WO2022066725A1 - Formation de réseaux faiblement supervisés bout-à-bout dans un mode multitâche au niveau de l'échantillon (supra-image) - Google Patents

Formation de réseaux faiblement supervisés bout-à-bout dans un mode multitâche au niveau de l'échantillon (supra-image) Download PDF

Info

Publication number
WO2022066725A1
WO2022066725A1 PCT/US2021/051495 US2021051495W WO2022066725A1 WO 2022066725 A1 WO2022066725 A1 WO 2022066725A1 US 2021051495 W US2021051495 W US 2021051495W WO 2022066725 A1 WO2022066725 A1 WO 2022066725A1
Authority
WO
WIPO (PCT)
Prior art keywords
pathological
image
supra
versus
neural network
Prior art date
Application number
PCT/US2021/051495
Other languages
English (en)
Inventor
Julianna IANNI
Saul KOHN
Sivaramakrishnan SANKARAPANDIAN
Rajath Elias SOANS
Original Assignee
Proscia Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Proscia Inc. filed Critical Proscia Inc.
Publication of WO2022066725A1 publication Critical patent/WO2022066725A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10056—Microscopic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images

Definitions

  • This disclosure relates generally to machine learning, e.g., in the context of pathology, such as dermatopathology.
  • a supra-image level weak label provides information for its supra-image rather than the individual constituent images. Labelling constituent images with the weak label from their supra-image and using them separately can introduce noise into the training process, because one constituent image may contain no features relevant to its label. That is, ignoring the connection of the constituent images that form a supra-image and simply using them separately to train a machine learning classifier produces inaccurate and unsatisfactory results.
  • weakly-supervised networks have been trained to perform a single task on a single image or image sub-region.
  • the task is often either classification, where input data is sorted into one or more output classes, or regression, where a single number (e.g., a probability of a particular classification) is predicted based on the input data. If two classifications on the same input data are desired, then two networks, one for each classification, would be required, according to past techniques.
  • a computer-implemented method of classifying a novel supra-image as one of a plurality of pathological classes using an electronic neural network to perform a plurality of binary classification tasks includes: receiving the novel supra-image; providing the novel supra-image to the electronic neural network that has been trained using a training dataset including at least one supra-image, each supra-image associated with a respective supra-image label indicating a pathological class of the plurality of pathological classes, each supra-image including a plurality of images, each image corresponding to a plurality of components, where the training dataset provides at least one batch of components, where the electronic neural network has been trained by: forward propagating the at least one batch of components, and their respective labels, through the electronic neural network, where the electronic neural network includes a plurality of task-specific branches, one task-specific branch corresponding to each of the binary pathological classification tasks, each task-specific branch including a plurality of respective task-specific layers, at least one respective aggregation of instances layer, and
  • the plurality of binary pathological classification tasks can include: melanocytic high risk versus melanocytic medium risk, melanocytic medium risk versus melanocytic low risk, and melanocytic low risk versus melanocytic high risk.
  • the plurality of binary pathological classification tasks can include: atypical vs. benign, atypical vs. malignant, and benign vs. malignant.
  • the plurality of binary pathological classification tasks can include: a first Gleason score versus a second Gleason score, the second Gleason score versus a third Gleason score, and the third Gleason score versus the first Gleason score.
  • the plurality of binary pathological classification tasks can include: a first survival quantification versus a second survival quantification, the second survival quantification versus a third survival quantification, and the first survival quantification versus the third survival quantification.
  • the plurality of binary pathological classification tasks can include: a first prognosis versus a second prognosis, the second prognosis versus a third prognosis, and the first prognosis versus the third prognosis.
  • the plurality of binary pathological classification tasks can include: a first drug response versus a second drug response, the second drug response versus a third drug response, and the first drug response versus the third drug response.
  • the plurality of pathological classes can consist of a number c of pathological classes, and the multiple pathological tasks can consist of a number c(c- 1 )/2 of binary classification tasks.
  • Each component can include a feature vector.
  • the plurality of pathological classes can include a plurality of dermatopathological classes.
  • the system includes a processor; and a memory communicatively coupled to the processor, the memory storing instructions which, when executed on the processor, perform operations including: receiving the novel supra-image; providing the novel supra- image to the electronic neural network that has been trained using a training dataset including at least one supra-image, each supra-image associated with a respective supra-image label indicating a pathological class of the plurality of pathological classes, each supra-image including a plurality of images, each image corresponding to a plurality of components, where the training dataset provides at least one batch of components, where the electronic neural network has been trained by: forward propagating the at least one batch of components, and their respective labels, through the electronic neural network, where the electronic neural network includes a plurality of task-specific branches, one task-specific branch corresponding to each of the binary pathological classification tasks, each task-specific branch including a plurality of respective task-specific layers, at least one respective aggregation of instances layer, and at least one respective output layer, where each task-specific branch is configured to produce, for a given
  • the plurality of binary pathological classification tasks can include: melanocytic high risk versus melanocytic medium risk, melanocytic medium risk versus melanocytic low risk, and melanocytic low risk versus melanocytic high risk.
  • the plurality of binary pathological classification tasks can include: atypical vs. benign, atypical vs. malignant, and benign vs. malignant.
  • the plurality of binary pathological classification tasks can include: a first Gleason score versus a second Gleason score, the second Gleason score versus a third Gleason score, and the third Gleason score versus the first Gleason score.
  • the plurality of binary pathological classification tasks can include: a first survival quantification versus a second survival quantification, the second survival quantification versus a third survival quantification, and the first survival quantification versus the third survival quantification.
  • the plurality of binary pathological classification tasks can include: a first prognosis versus a second prognosis, the second prognosis versus a third prognosis, and the first prognosis versus the third prognosis.
  • the plurality of binary pathological classification tasks can include: a first drug response versus a second drug response, the second drug response versus a third drug response, and the first drug response versus the third drug response.
  • the plurality of pathological classes can consist of a number c of pathological classes, and the multiple pathological tasks can consist of a number c(c- 1 )/2 of binary classification tasks.
  • Each component can include a feature vector.
  • the plurality of pathological classes can include a plurality of dermatopathological classes.
  • Fig. 1 is a schematic diagram depicting an example supra-image, its constituent images, a tiling of one of its constituent images, and vector representations of the tiles of the constituent image according to various embodiments;
  • FIG. 2 is a schematic diagram of an architecture of a system that uses a weakly-supervised neural network to perform multiple tasks according to various embodiments;
  • FIG. 3 is a flow diagram for a method of iteratively training, at the supra- image level, a neural network to classify supra-images according to various embodiments;
  • FIG. 4 is a flow diagram for a method of automatically classifying a supra- image according to various embodiments
  • FIG. 5 is a schematic diagram of a hardware computer system suitable for implementing various embodiments
  • FIG. 6 is a schematic diagram of the system architecture of an example reduction to practice
  • Fig. 7 is a schematic diagram representing a hierarchical classification technique implemented by the reduction to practice of Fig. 6;
  • Fig. 8 depicts receiver operating characteristic curves for the neural networks implemented by the reduction to practice of Fig. 6;
  • Fig. 9 depicts a chart comparing reference lab performance on the same test set when trained on consensus and non-consensus data.
  • Fig. 10 depicts a chart depicting mean and standard deviation sensitivity to melanoma versus percentage reviewed for 1 ,000 simulated sequentially accessioned datasets, drawn from reference lab confidence scores.
  • Embodiments can use weakly-labeled supra-images to train a machine learning algorithm, such as an electronic neural network, in a manner that provides superior classification results in comparison to existing techniques.
  • some embodiments provide a single network that can be trained to perform multiple tasks on supra-images in a weakly supervised manner using multi-instance learning. While previous work in multiple-instance learning has trained a single network to perform a single task, such as classification or regression for single images or image subregions, some embodiments extend the multiple-instance framework for a single network to an arbitrary number of tasks, which can be trained at the same time as one another, and be used to predict different attributes of the supra-image input data simultaneously.
  • Fig. 1 is a schematic diagram 100 depicting an example supra-image 102, its constituent images 104, a tiling 108 of one of its constituent images 106, and vector representations 112 of the tiles of the constituent image 106 according to various embodiments.
  • the term “supra-image” includes one or more constituent images of a specimen.
  • the specimen may be a medical specimen, a landscape specimen, or any other specimen amenable to image capture.
  • a supra-image may represent images from a single resection or biopsy (the supra-image) constituting several slides (the constituent images).
  • the supra-image may be a three-dimensional volume representing the results of a radiological scan such as a Computer Tomography (CT) or Magnetic Resonance Imaging (MRI) scan, and the constituent images may include two- dimensional slices of the three-dimensional volume.
  • CT Computer Tomography
  • MRI Magnetic Resonance Imaging
  • the images forming a supra-image may be of tissue stained with Hematoxylin and Eosin (H&E), and a label may be associated with the supra-image, for example, the diagnosis rendered by the pathologist.
  • H&E Hematoxylin and Eosin
  • a supra- image may be of any type of specimen in any field, not limited to pathology, e.g., a set of satellite images.
  • supra-image 102 may represent a three-dimensional volume, by way of non-limiting examples.
  • Supra-image 102 may be, for example, a representation of a CT or MRI scan.
  • Images 104 represent the constituent images of supra-image 102.
  • images 104 may be slices derived from, or used to derive, a CT or MRI scan, or may be whole-slide images, e.g., representing multiple images from a biopsy of a single specimen.
  • each constituent image of a supra-image may be broken down into a number of tiles, which may be, e.g., 128 pixels by 128 pixels.
  • image 106 of constituent images 104 may be partitioned into tiles, such as tile 110, to form partitioned image 108.
  • an individual tile may be represented by one or more corresponding feature vectors.
  • Such feature vectors may be obtained from tiles using a separate neural network, trained to produce feature vectors from tiles.
  • Each such feature vector may encode the presence or absence of one or more features in the tile that it represents.
  • Each feature vector may be in the form of a tuple of numbers.
  • feature vectors 112 represent the tiles of partitioned image 108.
  • feature vector 114 may correspond to and represent a presence or absence of a particular feature in tile 110.
  • each component is implemented as a tile of a constituent image of a supra-image.
  • each component is implemented as a vector, such as a feature vector, that represents and corresponds to a respective tile in a constituent image of a supra-image.
  • weakly-supervised networks were trained to operate either only in the specific case of a weak label per-image, or using a downstream classifier or alternative numerical method to combine the output of a weakly-supervised classifier from the image level to the supra-image level.
  • the former case restricts the usability of a trained network, while the latter relies on two models’ or methods’ performance to generate and combine image-level classifications to produce a representative supra-image level classification.
  • Multi-task learning often improves performance when compared to multiple models performing the tasks individually. This may be because the tasks can act as implicit regularizers, stopping one task from overfitting, since other tasks require the same input data representation. Also, some tasks may be easier than others to learn, and training them together can lead to a faster convergence on useful data representations for all of the tasks. Further, training models in a multi-task framework means that there are fewer models for a team/organization to verify and maintain. [0036] III. Description of Example Embodiments
  • Some embodiments provide weakly-supervised multiple-instance multitask learning at the supra-image level. Some embodiments train a neural network in a weakly-supervised fashion, using collections of components from images constituting supra-images as the input data, with a single label per collection. Some embodiments provide a trained neural network that is able to predict multiple different attributes of an input supra-image simultaneously. Some embodiments provide a trained network that is capable of performing an arbitrary number and variety of tasks, e.g., both classification and regression.
  • Some embodiments utilize multi-task learning as a method specifically of handling noisy data labels (e.g., training corpora in which some small proportion of labels, such as less than 1 %, are incorrect, or labels associated with phenomena that have no objective ground truth, such as cancer risk categories, where different human classifiers may arrive at different classifications for the same data).
  • noisy data labels e.g., training corpora in which some small proportion of labels, such as less than 1 %, are incorrect, or labels associated with phenomena that have no objective ground truth, such as cancer risk categories, where different human classifiers may arrive at different classifications for the same data.
  • some embodiments provide, for the first time, the ability to: implement weak supervision at the specimen-level, use multi-task learning to minimize the impact of noisy labels, and perform multiple tasks in a neural network to solve problems, e.g., in the domain of dermatopathology.
  • Fig. 2 is a schematic diagram of an architecture of a system 200 that uses a weakly-supervised neural network to perform multiple tasks according to various embodiments.
  • system 200 includes a neural network with shared representation layers 204, followed by individual task-specific representation layers 206, each of which feeds into a respective instance (component) aggregation layer 208, each of which is coupled to a respective output layer 210.
  • the weights and biases of the various layers of system 200 are determined, as described in detail herein in reference to Fig. 3.
  • one or more attributes of a novel input supra-image are determined by the trained system 200, as described in detail herein in reference to Fig. 4.
  • System 200 may be implemented using the hardware of system 500, as shown and described herein in reference to Fig. 5, for example.
  • some embodiments forego the typical multi-class formulation, in which the network is trained to accurately separate c classes simultaneously.
  • some embodiments break the problem into c(c-1)/2 binary (i.e., two- class) classification tasks in a multi-task framework.
  • such embodiments can divide the problem into tasks such that each subnetwork of the model can be trained to focus its attention on only the features necessary to distinguish between a single pair of classes at a time.
  • some embodiments are trained to individually identify the boundaries between each pair of classes: high and intermediate, low and intermediate, and low and high.
  • system 200 may include a first output layer 212 that distinguishes between class A and class B, a second output layer 214 that distinguishes between class B and class C, and a third output layer 216 that distinguishes between class A and class C. More generally, system may include c(c-1 )/2 output layers 210 for classifying a supra-image into c > 3 classes.
  • melanocytic risk may be characterized as high for cancerous invasive melanoma, medium for melanoma that has not spread past the dermis in situ, and low for benign or dysplastic conditions.
  • three-class classifications suitable for implementations include: a first, second, and third Gleason score (e.g., Gleason 2-4, 5-7, or 8-10); a first, second, and third survival quantification (e.g., low, medium, or high risk, correlating to varying expected survival time in months, such as less than 3 months, 3 months to 12 months, or greater than 12 months); a first, second, and third prognosis (e.g., recovery, hospitalization, or death); and a first, second, and third drug response (e.g., nonresponder, moderate responder, strong responder).
  • Gleason score e.g., Gleason 2-4, 5-7, or 8-10
  • survival quantification e.g., low, medium, or high risk, correlating to varying expected survival time in months, such as less than 3 months, 3 months to 12 months, or greater than 12 months
  • a first, second, and third prognosis e.g., recovery, hospitalization, or
  • embodiments can utilize (and predict) more than one weak label per supra-image.
  • three branches of the network could be used to distinguish between melanocytic high/medium/low risk, while a fourth branch could be used to predict some other number, e.g., a survival quantification.
  • each image in a supra-image is divided into a mosaic of tiles, e.g., squares of 128 pixels-per-side.
  • a sampled collection of such tiles, or feature vector representations thereof, small enough to be stored in the available volatile memory of the training computer, and labeled with the label of the supra-image from which the tiles are obtained, may serve as a single element of the training corpus for weakly-supervised iterative training according to various embodiments. Multiple such labeled collections of components may comprise a full training corpus. No region-of- interest need be identified.
  • An example iterative training technique that accommodates current hardware volatile memory limitations is shown and described presently in reference to Fig. 3.
  • Fig. 3 is a flow diagram for a method 300 of iteratively training, at the supra-image level, a neural network to classify supra-images, according to various embodiments.
  • Method 300 may be implemented using system architecture as shown and described herein in reference to Fig. 2, as instantiated by system 500, as shown and described herein in reference to Fig. 5.
  • an embodiment iteratively accepts as input collections of components of a supra-image from a training corpus of supra-images.
  • Current hardware e.g., Graphical Processing Units or GPUs
  • RAM Random Access Memory
  • each image of a supra-image is typically too large to feed into the hardware used to hold and train the deep learning neural network. Therefore, some embodiments train a weakly supervised neural network at the supra-image level, within these hardware limitations, by sampling (e.g., randomly sampling) components from constituent images of supra-images into collections of components that are close to the maximum size the hardware is able to hold in RAM.
  • the random sampling may not take into account which image from a supra-image the components are drawn from; components may be randomly drawn without replacement from a common pool for the supra-image.
  • the sampling can be performed several times for a given supra-image, creating more than one collection to train with for a given supra-image. Multiple such collections may form a partition of a given supra-image; that is, the set-theoretic union of the collections from a single supra-image may cover the entire supra-image, and the set-theoretic intersection of such collections may be empty.
  • method 300 accesses a training corpus of supra-images.
  • the supra-images may be in any field of interest.
  • the supra-images include or may be otherwise associated with weak labels.
  • the supra-images and weak labels may be obtained from an electronic clinical records system, such as an LIS.
  • the supra-images maybe accessed over a network communication link, or from electronic persistent memory, by way of non-limiting examples.
  • the training corpus may include hundreds, thousands, or even tens of thousands or more supra-images.
  • method 300 selects a batch of supra-images for processing.
  • the training corpus of supra-images with supra-image level labels to be used for training is divided into one or more batches of one or more supra-images.
  • the loss incurred by the network is computed over all batches through the actions of 304, 306, 308, 310, 312, and 314.
  • the losses over all of the batches are accumulated e.g., according to the Overall Loss, described in detail below, and then the weights and biases of the network are updated, at which point the accumulated loss is reset, and the process repeats until the iteration is complete.
  • method 300 samples, e.g., randomly samples, a collection of components from the batch of supra-images selected at 304.
  • each batch of supra-images is identified with a respective batch of collections of components, where each collection of components includes one or more components sampled, e.g., randomly sampled, from one or more images from a single supra-image in the batch of supra-images.
  • the term “batch” may refer to both a batch of one or more supra-images and a corresponding batch of collections of components from the batch of one or more supra-images.
  • Embodiments may not take into account which constituent image a given component in a collection comes from; components in the collection may be randomly drawn without replacement from a common pool for a given supra-image. Each collection of components is labeled according to the label(s) of the supra-image making up the images from which the components from the collection are drawn.
  • the components may be tiles of images within the selected supra-image batch, or may be feature vectors representative thereof.
  • the collections of components, when implemented as tiles, may form a partition of a given supra- image, and when implemented as vectors, the corresponding tiles may form a partition.
  • Embodiments may iterate through a single batch, i.e., a batch of collections of components, through the actions of 306, 308, and 310, until all components from the images of the supra-images for the batch are included in some collection of components that is forward propagated through the network. Embodiments may iterate through all of the batches through the actions of 304, 306, 308, 310, 312, and 314 to access the entire training dataset to completely train a network.
  • the collection of components sampled at 306 is forward propagated through the neural network to compute loss. Briefly, when the collection of components that is forward propagated through the multiple-instance learning neural network, the network's prediction is compared to the weak label for the collection. The more incorrect it is, the larger the loss value. Such a loss value is accumulated each time a collection of components is propagated through the network, until all collections of components in the batch are used and the overall loss for that batch is determined. The actions outlined in this paragraph are elaborated upon and described in detail presently.
  • the network will have at least one layer for a shared data representation of a component, which is subsequently passed to the task-specific branches.
  • Each task-specific branch could, in of itself, represent a weakly-supervised neural network. It includes a number of neural network layers, followed by an aggregation of the component representations, and layers corresponding to the final output.
  • the prediction of a given task t and batch b is denoted y b t .
  • the sampled collection of components is presented to the network, with a weak label y.
  • K batch of collections of size N b will have a list of weak labels y b .
  • the label y corresponds to the correct prediction for at least one of the tasks. Note that some labels may be irrelevant to some tasks.
  • the overall loss is determined.
  • the overall loss may be characterized as follows, by way of non-limiting example: 112
  • the parameters may be characterized as follows. [0055]
  • the term N b represents the number of collections in a batch
  • the term N t represents the number of batches in the training corpus
  • the term N w represents the number of weights in the network.
  • a t represents the weight assigned to every prediction in task t. This can be thought of as the overall importance of a given task. This importance governs the extent to which each task contributes to the overall loss, and therefore the relative extent to which performance at each task is optimized during training.
  • a t may represent the ranked importance of each task in terms of clinical importance (e.g., which tasks are most critical).
  • Other embodiments may use a larger a t value for a task t that typically has lower performance in comparison to other tasks. (For example, the inventors have seen in practice that melanocytic high vs. medium risk is a more difficult task for the model to perform. If this performance is valued above other tasks, an embodiment could increase its a t value or correspondingly decrease the alpha values associated with the other tasks). Without prior knowledge of these requirements or otherwise, a t may be set to one for all tasks t.
  • p b t represents the weight assigned on a batch-by-batch basis for task t. This corresponds to the importance of a given task-batch combination. For a binary classification task that does not correspond to the ground-truth class of data in a batch, this value can be set to zero to ignore the prediction of that task arm in the overall loss computation. For example, for the task of classifying between high-risk and medium-risk, batch data classified as low-risk may be masked by being weighted zero.
  • c b t H t (y b t , y b t> ) represents the weighted cost function for a particular task t.
  • the cost function on a basic level, calculates how wrong a prediction is - producing a larger number for a worse answer - in order for the loss function to update the model weights proportionally.
  • cost function In binary classification, there are several commonly used cost functions, such as binary cross-entropy.
  • the parameters for this weighted function are y b t , the predicted value, y b t , the ground-truth, and c b t , the class weight associated with that task: the relative proportion of the number of times that task will be calculated, given the ground-truth values in the dataset.
  • the B vs. C task may be weighted more than the A vs. B and A vs. C tasks.
  • the term A represents the weight assigned to l_2-regularization, which corresponds to stopping the model from overfitting by taxing the cumulative size of the weights in the network by this amount.
  • 2 represents the L2 norm of the weights in the network, where / indexes weights and N w is the total number of weights in the network.
  • method 300 determines whether there are additional collections of components from the batch selected at 304 that have not yet been processed. If so, control reverts to 306, where another collection of components is selected for processing as described above. If not, then control passes to 312.
  • method 300 back propagates the accumulated loss to update the weights and biases of the neural network. That is, after iterating through the collections of components from a single batch, the neural network weights and biases are updated according to the magnitude of the aggregated loss.
  • Method 300 may implement gradient descent to perform actions of 312. The actions of 312 may repeat over all batches in the dataset.
  • method 300 determines whether there are additional batches of supra-images from the training corpus accessed at 302 that have not yet been processed during the current iteration. Embodiments may iterate over the batches to access the entire training dataset. If additional batches exist, then control reverts to 304, where another batch of one or more supra-images is selected. Otherwise, control passes to 316. The repetitions may continue, e.g., until convergence, in order to train the network for optimal performance across all tasks.
  • Embodiments may train the neural networks for hundreds, or even thousands or more, of epochs.
  • method 300 provides the neural network that has been trained using the training corpus accessed at 302.
  • Method 300 may provide the trained neural network in a variety of ways.
  • the trained neural network is stored in electronic persistent memory.
  • the neural network is made available on a network, such as the internet.
  • an interface to the trained neural network is provided, such as a Graphical User Interface (GUI) or Application Program Interface (API).
  • GUI Graphical User Interface
  • API Application Program Interface
  • Fig. 4 is a flow diagram for a method 400 of automatically classifying a supra-image according to various embodiments.
  • Method 400 may use a neural network trained according to method 300 as shown and described herein in reference to Fig. 3.
  • Method 400 may be implemented by system 500, as shown and described herein in reference to Fig. 5.
  • a supra-image is obtained.
  • the supra-image may be in any field.
  • the supra-image may be obtained over a network link or by retrieval from persistent storage, by way of non-limiting example.
  • the neural network is applied to the supra-image obtained at 402.
  • the supra-image may be broken down into parts (e.g., components or sets of components) and the parts may be individually passed through the network up to a particular layer, where the features from the various parts are aggregated, and then the parts are passed through to a further particular layer, where the features are again aggregated, until all parts are iteratively passed and all features aggregated such that one or more outputs are produced.
  • Three (or more) output layers may be present (e.g., as shown and described herein in reference to Fig. 2). In operation, each such layer provides an output. These outputs may be independently useful.
  • the multiple outputs may be synthesized to produce a final, single output.
  • post-processing of the output layers’ output is instituted to obtain a single output from the network, where the single output reflects (broadly) a score, e.g., a severity score, between zero and one, inclusive.
  • a score e.g., a severity score, between zero and one, inclusive.
  • the higher the score the more likely the specimen is (according to the model) to contain an invasive melanoma (rather than a benign nevus, at the other end of the spectrum).
  • Such embodiments may obtain the score by synthesizing an output from two or more of the multiple tasks. For example, some embodiments synthesize the outputs from tasks low-risk vs. high-risk and low- risk vs. intermediate-risk. Such embodiments may take the maximum score of these two tasks to assign a severity score, and use logic based on these scores to assign an output classification, e.g., Melanocytic (lower risk), Suspect, or High Risk.
  • an output classification e.g., Melanocytic (lower risk), Suspect, or High Risk.
  • method 400 provides the output.
  • the output may be provided by displaying a corresponding datum to a user of method 400, e.g., on a computer monitor.
  • a datum may indicate the presence or absence of a feature of interest in the supra-image, by way of non-limiting example.
  • Fig. 5 is a schematic diagram of a hardware computer system 500 suitable for implementing various embodiments.
  • Fig. 5 illustrates various hardware, software, and other resources that can be used in implementations of method 200 as shown and described herein in reference to Fig. 2, method 300 as shown and described herein in reference to Fig. 3, and/or method 400 as shown and described herein in reference to Fig. 4.
  • System 500 includes training corpus source 520 and computer 501. Training corpus source 520 and computer 501 may be communicatively coupled by way of one or more networks 504, e.g., the internet.
  • Training corpus source 502 may include an electronic clinical records system, such as an LIS, a database, a compendium of clinical data, or any other source of supra-images suitable for use as a training corpus as disclosed herein.
  • Computer 501 may be implemented as any of a desktop computer, a laptop computer, can be incorporated in one or more servers, clusters, or other computers or hardware resources, or can be implemented using cloud-based resources.
  • Computer 501 includes volatile memory 514 and persistent memory 512, the latter of which can store computer-readable instructions, that, when executed by electronic processor 510, configure computer 501 to perform any of methods 200, 300, and/or 400, as shown and described herein.
  • Computer 501 further includes network interface 508, which communicatively couples computer 501 to training corpus source 502 via network 504. Other configurations of system 500, associated network connections, and other hardware, software, and service resources are possible.
  • This Section presents an example reduction to practice.
  • the example reduction to practice is configured to perform hierarchical classification of digitized whole-slide image specimens into six classes defined by their morphological characteristics, including classification of “Melanocytic Suspect” specimens likely representing melanoma or severe dysplastic nevi.
  • the reduction to practice was trained on 7,685 images from a single lab (the reference lab), including the largest set of triple-concordant melanocytic specimens compiled to date, and tested the system on 5,099 images from two distinct validation labs.
  • the reduction to practice achieved Area Underneath the Receiver Operating Characteristics Curve (AUC) values of 0.93 classifying Melanocytic Suspect specimens on the reference lab, 0.95 on the first validation lab, and 0.82 on the second validation lab.
  • AUC Receiver Operating Characteristics Curve
  • MPATH-Dx The Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis (MPATH-Dx; “MPATH” hereafter) reporting schema was introduced by Piepkorn, et al., The mpath-dx reporting schema for melanocytic proliferations and melanoma, Journal of the American Academy of Dermatology, 70(1): 131 -141 , 2014 to provide a precise and consistent framework for dermatopathologists to grade the severity of melanocytic proliferation in a specimen.
  • MPATH scores are enumerated from I to V, with I denoting a benign melanocytic lesion and V denoting invasive melanoma. It has been shown that discordance rates are related to the MPATH score, with better inter-observer agreement on both ends of the scale than in the middle.
  • a tool that allows labs to sort and prioritize melanoma cases in advance of pathologist review could improve turnaround time, allowing pathologists to review cases requiring faster turnaround time early in the day. This is particularly important as shorter turnaround time is correlated with improved overall survival for melanoma patients. It could also alleviate common lab bottlenecks such as referring cases to specialized dermatopathologists, or ordering additional tissue staining beyond the standard H&E. These contributions are especially important as the number of skin biopsies performed per year has skyrocketed, while the number of practicing pathologists has declined.
  • Pantanowitz, et al An artificial intelligence algorithm for prostate cancer diagnosis in whole-slide images of core needle biopsies: a blinded clinical validation and deployment study, The Lancet Digital Health, 2(8):e407-e416, 2020 describes using pixel-wise annotations to develop a model trained on -550 whole-slide images that distinguish high-grade from low-grade prostate cancer.
  • this Section presents a reduction to practice that can classify skin cases for triage and prioritization prior to pathologist review.
  • the reduction to practice performs hierarchical melanocytic specimen classification into low (MPATH l-ll), Intermediate (MPATH III), or High (MPATH IV-V) diagnostic categories, allowing for prioritization of melanoma cases.
  • the reduction to practice was the first to classify skin biopsies at the specimen level through a collection of whole-slide images that represent the entirety of the tissue from a single specimen, e.g., a supra-image.
  • This training procedure is analogous to the process of a dermatopathologist, who reviews the full collection of scanned whole-slide images corresponding to a specimen to make a diagnosis.
  • the reduction to practice was trained and validated on the largest dataset of consensus-reviewed melanocytic specimens published to date.
  • the reduction to practice was built to be scalable and ready for the real-world, built without any pixel-level annotations, and incorporating the automatic removal of scanning artifacts.
  • the reduction to practice was trained using slides from 3511 specimens (consisting of 7685 whole-slide images) collected from a leading dermatopathology lab in a top academic medical center (Department of Dermatology at University of Florida College of Medicine), which is referred to as the “Reference Lab”.
  • the Reference Lab dataset consisted of both an uninterrupted series of sequentially- accessioned cases (69% of total specimens) and a targeted set, curated to enrich for rarer melanocytic pathologies (31 % of total specimens). Melanocytic specimens were only included in this set if three dermatopathologists’ consensus on diagnosis could be established.
  • the whole-slide images consisted exclusively of H&E-stained, formalin-fixed, paraffin-embedded dermatopathology tissue and were scanned using a 3DHistech P250 High Capacity Slide Scanner at an objective power of 20X, corresponding to 0.24pm/pixel.
  • the final classification given by the reduction to practice was one of six classes, defined by their morphologic characteristics:
  • Basaloid containing abnormal proliferations of basaloid-oval cells, primarily basal cell carcinoma of various types;
  • Squamous containing malignant squamoid epithelial proliferations, consisting primarily of squamous cell carcinoma (invasive and in situ);
  • the overall reference set was composed of 544 Basaloid, 530
  • Table 1 Counts of each of the general pathologies in the reference set from the Reference Lab, broken-out into specific diagnostic entities
  • specimen counts presented herein for the melanocytic classes reflect counts following three-way consensus review (see Section IV(C)). For training, validating, and testing the reduction to practice, this dataset was divided into three partitions by sampling at random without replacement with 70% of specimens used for training, and 15% used for each of validation and testing.
  • Specimens from Validation Lab 2 consisted of slides from 2066 specimens (2066 whole-slide images; each specimen represented by a single whole-slide image), with whole-slide images scanned using a Ventana DP 200 scanner at an objective power of 20X (0.47 pm/pixel). Note: specimen and whole-slide image counts above reflect specimens included in the study after screening melanocytic specimens for inter-pathologist consensus. Table 2 shows the class distribution for the Validation labs.
  • Fig. 6 is a schematic diagram of the system architecture 600 of an example reduction to practice.
  • the reduction to practice includes three main components: quality control 610, feature extraction 620, and hierarchical classification 630.
  • quality control 610 quality control 610
  • feature extraction 620 feature extraction 620
  • hierarchical classification 630 hierarchical classification 630.
  • a brief description of how the reduction to practice was used to classify a novel supra-image follows.
  • Each specimen 602, a supra-image was first segmented into tissue-containing regions, subdivided into 128x128 pixel tiles by tiling 604, and extracted at an objective power of 10X.
  • Each tile was passed through the quality control 610, which includes ink filtering 612, blur filtering 616, and image adaptation 614.
  • the image-adapted tiles were then passed through the feature extraction 620 stage, including a pretrained ResNet50 network 622, to obtain embedded vectors 624 as components corresponding to the tiles.
  • the embedded vectors 624 were propagated through the hierarchical classification 630 stage, including an upstream neural network 632 performing a binary classification between “Melanocytic Suspect” and “Rest”. Specimens that were classified as “Melanocytic Suspect” were fed into a first downstream neural network 634, which classified between “Melanocytic High Risk, Melanocytic Intermediate Risk” and “Rest”. The remaining specimens were fed into a second downstream “Rest” neural network 636, which classified between “Basaloid, Squamous, Melanocytic Low Risk” and “Other”. This classification process of the reduction to practice is described in detail presently.
  • Quality control 610 included ink filtering 612, blur filtering 616, and image adaptation 614.
  • Pen ink is common in labs migrating their workload from glass slides to whole-slide images where the location of possible malignancy was marked. This pen ink represented a biased distractor signal in training the reduction to practice that is highly correlated with malignant or High Risk pathologies.
  • Tiles containing pen ink were identified by a weakly supervised neural network trained to detect inked slides. These tiles were removed from the training and validation data and before inference on the test set. Areas of the image that were out of focus due to scanning errors were also removed to the extent possible by blur filtering 616 by setting a threshold on the variance of the Laplacian over each tile.
  • the reduction to practice adopted as its image adaptation 614 the image adaptation procedure in lanni 2020.
  • feature extraction 620 extracted informative features from the quality controlled, color-standardized tiles. To capture higher-level features in these tiles, they were propagated through a neural network (ResNet50; He, et al., Deep residual learning for image recognition, arXiv preprint arXiv: 1512.03385, 2015) trained on the ImageNet (Deng, et al., Imagenet: A large-scale hierarchical image database, In IEEE Conference on Computer Vision and Pattern Recognition, pages 248-255, 2009) dataset to embed each input tile into 1024 channel vectors which were then used in subsequent neural networks.
  • ResNet50 He, et al., Deep residual learning for image recognition, arXiv preprint arXiv: 1512.03385, 2015
  • the hierarchical neural network architecture was developed in order to classify both Melanocytic High and Intermediate Risk specimens with high sensitivity.
  • the upstream neural network 632 performed a binary classification between “Melanocytic Suspect” (defined as “High or Intermediate Risk”) and “Basaloid, Squamous, Low Risk”, or “Other” (which are collectively defined as the “Rest” class). Specimens that were classified as “Melanocytic Suspect” were fed into the downstream neural network 634, which further classified the specimen between “Melanocytic High Risk, Melanocytic Intermediate Risk” and “Rest”.
  • Each neural network 632, 634, 636 included four fully- connected layers (two layers of 1024 channels each, followed by two of 512 channels each). Each neuron in the three layers after the input layer was ReLU activated.
  • the three neural networks 632, 634, 636 in the hierarchy were trained under a weakly-supervised multiple-instance learning (MIL) paradigm. Each embedded tile was treated as an instance of a bag containing all quality-assured tiles of a specimen. Embedded tiles were aggregated using sigmoid-activated attention heads. To help prevent over-fitting, the training dataset included augmented versions of the tiles. Augmentations were generated with the following augmentation strategies: random variations in brightness, hue, contrast, saturation, (up to a maximum of 15%), Gaussian noise with 0.001 variance, and random 90° image rotations. The upstream binary “Melanocytic Suspect vs.
  • MIL weakly-supervised multiple-instance learning
  • Rest classification neural network 632 and the downstream “Rest” subclassifier neural network 636 were each trained end-to-end with cross-entropy loss.
  • the “Melanocytic Suspect” subclassifier neural network 634 was also trained with cross-entropy loss, but with a multi-task learning strategy. This subclassifier neural network 634 was presented with three tasks: differentiating “Melanocytic High Risk” from “Melanocytic Intermediate Risk” specimens, “Melanocytic High Risk” from “Rest” specimens, and “Melanocytic Intermediate Risk” from “Rest” specimens.
  • the training loss for this subclassifier neural network 634 was computed for each task, but was masked if it did not relate to the ground truth label of the specimen. Two out of three tasks were trained for any given specimen in a training batch. By training in this manner, the shared network layers were used as a generic representation of melanocytic pathologies, while the task branches learned to attend to specific differences to accomplish their tasks.
  • Fig. 7 is a schematic diagram representing a hierarchical classification technique 700 implemented by the reduction to practice of Fig. 6.
  • the hierarchal classification technique 700 may be implemented by hierarchal classification 630 as shown and described above in reference to Fig. 6.
  • Fig. 7 depicts Melanocytic Suspect Subclassifier 734, corresponding to the first downstream neural network 634 of Fig. 6, and depicts Rest subclassifier 736, corresponding to the second downstream neural network 636 of Fig. 6.
  • the predicted classes of an input specimen 702 e.g., a supra-image
  • the larger of the two confidence values 704 (see below for the confidence thresholding procedure) output from the upstream classifier determined which downstream classifier a specimen was passed to.
  • the hierarchical classification technique 700 performed classification with uncertainty quantification to establish a confidence score for each prediction using a Monte Carlo dropout method following a similar procedure as used by Gal et al., Dropout as a Bayesian approximation: Representing model uncertainty in deep learning, In International Conference on Machine Learning, pages 1050-1059, 2016.
  • the hierarchal classification technique 700 computed confidence threshold values for each predicted class following the procedure outlined in lanni 2020 by requiring classifications to meet a predefined a level of accuracy in the validation set.
  • Fig. 8 depicts Receiver Operating Characteristic (“ROC”) curves 800 for the neural networks implemented by the reduction to practice of Fig. 6.
  • ROC Receiver Operating Characteristic
  • Fig. 8 depicts such results for the upstream classifier (left column), the High & Melanocytic Intermediate classifier (middle column), and the Basaloid, Squamous, Low Risk Melanocytic & Rest classifier (right column), for the Reference Lab (first row), for Validation Lab 1 , (second row), and for Validation Lab 2 (third row).
  • AUC Area Underneath the ROC Curve
  • Table 3 shows metrics for selected diagnoses of clinical interest, based on the reference Lab test set, representing the classification performance of the individual diagnoses into their higher-level classes: e.g., a correct classification of “Melanoma” is the prediction “Melanocytic High Risk”. Results are class-weighted according to the relative prevalence in the test set.
  • Table 3 Metrics for selected diagnoses of clinical interest
  • the sensitivity of the reduction to practice to the Melanocytic Suspect class was found to be 0.83, 0.85 for the Melanocytic High and Intermediate risk classes, respectively.
  • the PPV to Melanocytic High Risk was found to be 0.57.
  • the dropout Monte Carlo procedure set the threshold for Melanocytic High Risk classification very high; specimens below this threshold were classified as Melanocytic Suspect, maximizing the sensitivity to this class.
  • the AUC values for Validation Lab 1 were 0.95, 0.88, 0.81 ,0.87, 0.87, 0.95, and 0.92 for the Basaloid, Squamous, Other, Melanocytic High Risk, Intermediate Risk, Suspect, and Low Risk classes, respectively and the AUC values for the same classes for Validation Lab 2 were 0.93, 0.92, 0.69, 0.76, 0.75, 0.82, and 0.92.
  • Fig. 9 depicts a chart 900 comparing reference lab performance on the same test set when trained on consensus and non-consensus data.
  • the melanocytic class referenced in chart 900 is defined as the Low, Intermediate and High Risk classes.
  • the sensitivity of the Melanocytic Intermediate and High Risk classes are defined with respect to the reduction to practice classifying these classes as suspect.
  • the PPV to melanocytic high risk in the non-consensus trained model was 0.33, while the consensus model was 0.57.
  • the first neural network was trained only including melanocytic specimens for which consensus was obtained under the diagnostic categories of MPATH l/ll, MPATH III, or M PATH IV/V.
  • the other neural network was trained by also including non-consensus data: melanocytic specimens whose diagnostic category was not agreed upon by the experts.
  • validation sets for both neural network versions and a common consensus test set derived from the Reference Lab were reserved. The sensitivities of the reduction to practice to different classes on both consensus and non-consensus data are shown in Fig.
  • This document discloses a reduction to practice capable of automatically sorting and triaging skin specimens with high sensitivity to Melanocytic Suspect cases prior to review by a pathologist.
  • prior art techniques may provide diagnostically-relevant information on a potential melanoma specimen only after a pathologist has reviewed the specimen and classified it as a Melanocytic Suspect lesion.
  • Fig. 10 depicts a chart 1000 depicting mean and standard deviation sensitivity to melanoma versus percentage reviewed for 1 ,000 simulated sequentially accessioned datasets, drawn from reference lab confidence scores.
  • chart 1000 depicts mean 1002 and standard deviation sensitivity 1002 to melanoma versus percentage reviewed for 1 ,000 simulated sequentially-accessioned datasets, drawn from Reference Lab confidence scores.
  • 95% of melanoma suspect cases are detected within the first 30% of cases, when ordered by melanoma suspect model confidence.
  • Fig. 10 demonstrates the resulting sensitivity to the Melanocytic Suspect class against the percentage of total specimens that a pathologist would have to review in this sorting scheme in order to achieve that sensitivity.
  • a pathologist would only need between 30% and 60% of the caseload to address all melanoma specimens according to this dataset.
  • the reduction to practice also enables other automated pathology workflows in addition to triage and prioritization of suspected melanoma cases. Sorting and triaging specimens into other classifications such as Basaloid could allow the majority of less complicated cases (such as basal cell carcinoma) to be directly assigned to general pathologists, or to dermatologists who routinely sign out such cases. Relevant to any system designed for clinical use is how well its performance generalizes to sites on which the system was not trained. Performance of the reduction to practice on the Validation Labs after calibration (as shown in Fig. 10) was in many cases close to that of the Reference Lab.
  • a computer-implemented method of classifying a novel supraimage as one of a plurality of pathological classes using an electronic neural network to perform a plurality of binary classification tasks comprising: receiving the novel supra-image; providing the novel supra-image to the electronic neural network that has been trained using a training dataset comprising at least one supraimage, each supra-image associated with a respective supra-image label indicating a pathological class of the plurality of pathological classes, each supra-image comprising a plurality of images, each image corresponding to a plurality of components, wherein the training dataset provides at least one batch of components, wherein the electronic neural network has been trained by: forward propagating the at least one batch of components, and their respective labels, through the electronic neural network, wherein the electronic neural network comprises a plurality of taskspecific branches, one task-specific branch corresponding to each of the binary pathological classification tasks, each task-specific branch comprising a plurality of respective task-specific layers, at least one respective aggregation of instances layer, and
  • Clause 2 The method of Clause 1 , wherein the plurality of binary pathological classification tasks comprises: melanocytic high risk versus melanocytic medium risk, melanocytic medium risk versus melanocytic low risk, and melanocytic low risk versus melanocytic high risk.
  • Clause 3 The method of Clause 1 or Clause 2, wherein the plurality of binary pathological classification tasks comprises: atypical vs. benign, atypical vs. malignant, and benign vs. malignant.
  • Clause 4 The method of any of Clauses 1-3, wherein the plurality of binary pathological classification tasks comprises: a first Gleason score versus a second Gleason score, the second Gleason score versus a third Gleason score, and the third Gleason score versus the first Gleason score.
  • Clause 5 The method of any of Clauses 1-4, wherein the plurality of binary pathological classification tasks comprises: a first survival quantification versus a second survival quantification, the second survival quantification versus a third survival quantification, and the first survival quantification versus the third survival quantification.
  • Clause 6 The method of any of Clauses 1-5, wherein the plurality of binary pathological classification tasks comprises: a first prognosis versus a second prognosis, the second prognosis versus a third prognosis, and the first prognosis versus the third prognosis.
  • Clause 7 The method of any of Clauses 1-6, wherein the plurality of binary pathological classification tasks comprises: a first drug response versus a second drug response, the second drug response versus a third drug response, and the first drug response versus the third drug response.
  • Clause 8 The method of any of Clauses 1-7, wherein the plurality of pathological classes consist of a number c of pathological classes, and wherein the multiple pathological tasks consist of a number c(c-1 )/2 of binary classification tasks.
  • Clause 9 The method of any of Clauses 1-8, wherein each component comprises a feature vector.
  • Clause 10 The method of any of Clauses 1-9, wherein the plurality of pathological classes comprises a plurality of dermatopathological classes.
  • Clause 11 The method of any of Clauses 1-10, wherein the training dataset provides a plurality of batches of components, and wherein the method further comprises repeating the forward propagating and the back propagating for another batch of components of the plurality of batches of components.
  • Clause 12 The method of any of Clauses 1-11 , wherein the electronic neural network comprises at least one layer for a shared data representation of components.
  • Clause 13 The method of any of Clauses 1-12, wherein each supraimage represents a biopsy.
  • Clause 14 The method of any of Clauses 1-13, wherein each image comprises a whole-slide image.
  • Clause 15 The method of any of Clauses 1-8 or 10-14, wherein each component comprises a 128-pixel-by-128-pixel square.
  • a system for classifying a novel supra-image as one of a plurality of pathological classes using an electronic neural network to perform a plurality of binary classification tasks comprising: a processor; and a memory communicatively coupled to the processor, the memory storing instructions which, when executed on the processor, perform operations comprising: receiving the novel supra-image; providing the novel supra-image to the electronic neural network that has been trained using a training dataset comprising at least one supra-image, each supra-image associated with a respective supra-image label indicating a pathological class of the plurality of pathological classes, each supra-image comprising a plurality of images, each image corresponding to a plurality of components, wherein the training dataset provides at least one batch of components, wherein the electronic neural network has been trained by: forward propagating the at least one batch of components, and their respective labels, through the electronic neural network, wherein the electronic neural network comprises a plurality of taskspecific branches, one task-specific branch corresponding to each of the binary pathological classification tasks,
  • Clause 17 The system of Clause 16, wherein the plurality of binary pathological classification tasks comprise: melanocytic high risk versus melanocytic medium risk, melanocytic medium risk versus melanocytic low risk, and melanocytic low risk versus melanocytic high risk.
  • Clause 18 The system of Clause 16 or Clause 17, wherein the plurality of binary pathological classification tasks comprises: atypical vs. benign, atypical vs. malignant, and benign vs. malignant.
  • Clause 19 The system of any of Clauses 16-18, wherein the plurality of binary pathological classification tasks comprises: a first Gleason score versus a second Gleason score, the second Gleason score versus a third Gleason score, and the third Gleason score versus the first Gleason score.
  • Clause 20 The system of any of Clauses 16-19, wherein the plurality of binary pathological classification tasks comprises: a first survival quantification versus a second survival quantification, the second survival quantification versus a third survival quantification, and the first survival quantification versus the third survival quantification.
  • Clause 21 The system of any of Clauses 16-20, wherein the plurality of binary pathological classification tasks comprises: a first prognosis versus a second prognosis, the second prognosis versus a third prognosis, and the first prognosis versus the third prognosis.
  • Clause 22 The system of any of Clauses 16-21 , wherein the plurality of binary pathological classification tasks comprises: a first drug response versus a second drug response, the second drug response versus a third drug response, and the first drug response versus the third drug response.
  • Clause 23 The system of any of Clauses 16-22, wherein the plurality of pathological classes consist of a number c of pathological classes, and wherein the multiple pathological tasks consist of a number c(c-1 )/2 of binary classification tasks.
  • Clause 24 The system of any of Clauses 16-23, wherein each component comprises a feature vector.
  • Clause 25 The system of any of Clauses 16-24, wherein the plurality of pathological classes comprises a plurality of dermatopathological classes.
  • Clause 26 The system of any of Clauses 16-25, wherein the training dataset provides a plurality of batches of components, and wherein the training further comprises repeating the forward propagating and the back propagating for another batch of components of the plurality of batches of components.
  • Clause 27 The system of any of Clauses 16-26, wherein the electronic neural network comprises at least one layer for a shared data representation of components.
  • Clause 28 The system of any of Clauses 16-27, wherein each supraimage represents a biopsy.
  • Clause 29 The system of any of Clauses 16-28, wherein each image comprises a whole-slide image.
  • Clause 30 The system of any of Clauses 16-23 or 25-30, wherein each component comprises a 128-pixel-by-128-pixel square.
  • a method of training an electronic neural network to perform a plurality of binary pathological classification tasks for classifying a novel supra-image as one of a plurality of pathological classes comprising: obtaining a training dataset comprising at least one supra-image, wherein each supra-image is associated with a respective supra-image label indicating a pathological class of the plurality of pathological classes, each supra-image comprising at least one image, each image corresponding to a plurality of components, wherein the training dataset provides at least one batch of components; forward propagating the at least one batch of components, and their respective supra-image labels, through the electronic neural network, wherein the electronic neural network comprises a plurality of task-specific branches, one task-specific branch corresponding to each of the binary pathological classification tasks, each task-specific branch comprising a plurality of respective taskspecific layers, at least one respective aggregation of instances layer, and at least one respective output layer, wherein each task-specific branch is configured to produce, for a given input batch of components,
  • Clause 32 The method of Clause 31 , wherein the plurality of binary pathological classification tasks comprise: melanocytic high risk versus melanocytic medium risk, melanocytic medium risk versus melanocytic low risk, and melanocytic low risk versus melanocytic high risk.
  • Clause 33 The method of Clause 31 or Clause 32, wherein the plurality of binary pathological classification tasks comprise: atypical vs. benign, atypical vs. malignant, and benign vs. malignant.
  • Clause 34 The method of any of Clauses 31-33, wherein the plurality of binary pathological classification tasks comprise: a first Gleason score versus a second Gleason score, the second Gleason score versus a third Gleason score, and the third Gleason score versus the first Gleason score.
  • Clause 35 The method of any of Clauses 31-34, wherein the plurality of binary pathological classification tasks comprise: a first survival quantification versus a second survival quantification, the second survival quantification versus a third survival quantification, and the first survival quantification versus the third survival quantification.
  • Clause 36 The method of any of Clauses 31-35, wherein the plurality of binary pathological classification tasks comprise: a first prognosis versus a second prognosis, the second prognosis versus a third prognosis, and the first prognosis versus the third prognosis.
  • Clause 37 The method of any of Clauses 31-36, wherein the plurality of binary pathological classification tasks comprise: a first drug response versus a second drug response, the second drug response versus a third drug response, and the first drug response versus the third drug response.
  • Clause 38 The method of any of Clauses 31-37, wherein the training dataset provides a plurality of batches of components, and wherein the method further comprises repeating the forward propagating and the back propagating for another batch of components of the plurality of batches of components.
  • Clause 39 The method of any of Clauses 31-38, wherein the plurality of pathological classes consist of a number c of pathological classes, and wherein the multiple pathological tasks consist of a number c(c-1 )/2 of binary classification tasks.
  • Clause 40 The method of any of Clauses 31-39, wherein the electronic neural network comprises at least one layer for a shared data representation of components.
  • Clause 41 The method of any of Clauses 31-40, wherein each supraimage represents a biopsy.
  • Clause 42 The method of any of Clauses 31-41 , wherein each image comprises a whole-slide image.
  • Clause 43 The method of any of Clauses 31-42, wherein each component comprises a 128-pixel-by-128-pixel square.
  • Clause 44 The method of any of Clauses 31-42, wherein each component comprises a feature vector.
  • Clause 45 The method of any of Clauses 31-44, wherein the plurality of pathological classes comprise a plurality of dermatopathological classes.
  • Clause 46 Computer readable storage comprising a representation of an electronic neural network produced by operations of any of Clauses 31-45.
  • Clause 47 An electronic computer comprising at least one electronic processor communicatively coupled to electronic persistent memory comprising instructions that, when executed by the at least one processor, configure the at least one processor to perform operations of any of Clauses 1-15 or 31-45.
  • Clause 48 At least one non-transitory computer readable storage medium comprising instructions that, when executed by at least one electronic processor, configure the at least one processor to perform operations of any of Clauses 1-15 or 31-45.
  • Certain embodiments can be performed using a computer program or set of programs.
  • the computer programs can exist in a variety of forms both active and inactive.
  • the computer programs can exist as software program(s) comprised of program instructions in source code, object code, executable code or other formats; firmware program(s), or hardware description language (HDL) files. Any of the above can be embodied on a transitory or non-transitory computer readable medium, which include storage devices and signals, in compressed or uncompressed form.
  • Exemplary computer readable storage devices include conventional computer system RAM (random access memory), ROM (read-only memory), EPROM (erasable, programmable ROM), EEPROM (electrically erasable, programmable ROM), and magnetic or optical disks or tapes.
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable, programmable ROM
  • EEPROM electrically erasable, programmable ROM

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • Computing Systems (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

Des exemples peuvent fournir un réseau neuronal électronique qui a été entraîné à l'aide d'au moins une supra-image associée à une étiquette de supra-image indiquant une classe pathologique par : propagation vers l'avant d'au moins un lot de composants à travers le réseau neuronal électronique, le réseau neuronal électronique comprenant une pluralité de branches spécifiques de tâche, une branche spécifique de tâche correspondant à chacune d'une pluralité de tâches de classification pathologique binaire ; renvoi du ou des lots de composants par rapport à une fonction de perte globale pour obtenir des poids révisés pour le réseau neuronal électronique, la fonction de perte globale comprenant une fonction de perte spécifique de tâche pour chaque tâche ; et mise à jour des poids du réseau neuronal électronique. Le réseau neuronal électronique est conçu pour fournir une classe pathologique de sortie de la pluralité de classes pathologiques pour une supra-image d'entrée.
PCT/US2021/051495 2020-09-23 2021-09-22 Formation de réseaux faiblement supervisés bout-à-bout dans un mode multitâche au niveau de l'échantillon (supra-image) WO2022066725A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202063082276P 2020-09-23 2020-09-23
US63/082,276 2020-09-23

Publications (1)

Publication Number Publication Date
WO2022066725A1 true WO2022066725A1 (fr) 2022-03-31

Family

ID=80845775

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2021/051495 WO2022066725A1 (fr) 2020-09-23 2021-09-22 Formation de réseaux faiblement supervisés bout-à-bout dans un mode multitâche au niveau de l'échantillon (supra-image)

Country Status (1)

Country Link
WO (1) WO2022066725A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11423678B2 (en) 2019-09-23 2022-08-23 Proscia Inc. Automated whole-slide image classification using deep learning
CN116805926A (zh) * 2023-08-21 2023-09-26 上海飞旗网络技术股份有限公司 网络业务类型识别模型训练方法、网络业务类型识别方法
US11861881B2 (en) 2020-09-23 2024-01-02 Proscia Inc. Critical component detection using deep learning and attention

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190286880A1 (en) * 2018-03-16 2019-09-19 Proscia Inc. Deep learning automated dermatopathology
US20190325621A1 (en) * 2016-06-24 2019-10-24 Rensselaer Polytechnic Institute Tomographic image reconstruction via machine learning
US20200058126A1 (en) * 2018-08-17 2020-02-20 12 Sigma Technologies Image segmentation and object detection using fully convolutional neural network
US20200129263A1 (en) * 2017-02-14 2020-04-30 Dignity Health Systems, methods, and media for selectively presenting images captured by confocal laser endomicroscopy
US20200226422A1 (en) * 2019-01-13 2020-07-16 Lightlab Imaging, Inc. Systems and methods for classification of arterial image regions and features thereof

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190325621A1 (en) * 2016-06-24 2019-10-24 Rensselaer Polytechnic Institute Tomographic image reconstruction via machine learning
US20200129263A1 (en) * 2017-02-14 2020-04-30 Dignity Health Systems, methods, and media for selectively presenting images captured by confocal laser endomicroscopy
US20190286880A1 (en) * 2018-03-16 2019-09-19 Proscia Inc. Deep learning automated dermatopathology
US20200058126A1 (en) * 2018-08-17 2020-02-20 12 Sigma Technologies Image segmentation and object detection using fully convolutional neural network
US20200226422A1 (en) * 2019-01-13 2020-07-16 Lightlab Imaging, Inc. Systems and methods for classification of arterial image regions and features thereof

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
JI JUNYI: "Gradient-based Interpretation on Convolutional Neural Network for Classification of Pathological Images", 2019 INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND COMPUTER APPLICATION (ITCA), IEEE, 20 December 2019 (2019-12-20), pages 83 - 86, XP033770782, DOI: 10.1109/ITCA49981.2019.00026 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11423678B2 (en) 2019-09-23 2022-08-23 Proscia Inc. Automated whole-slide image classification using deep learning
US11462032B2 (en) 2019-09-23 2022-10-04 Proscia Inc. Stain normalization for automated whole-slide image classification
US11861881B2 (en) 2020-09-23 2024-01-02 Proscia Inc. Critical component detection using deep learning and attention
CN116805926A (zh) * 2023-08-21 2023-09-26 上海飞旗网络技术股份有限公司 网络业务类型识别模型训练方法、网络业务类型识别方法
CN116805926B (zh) * 2023-08-21 2023-11-17 上海飞旗网络技术股份有限公司 网络业务类型识别模型训练方法、网络业务类型识别方法

Similar Documents

Publication Publication Date Title
Dov et al. Weakly supervised instance learning for thyroid malignancy prediction from whole slide cytopathology images
EP3155592B1 (fr) Prédiction d'une récurrence du cancer du sein directement à partir de caractéristiques d'image calculées à partir de lames de tissu d'immunohistopathologie numérisées
WO2022066725A1 (fr) Formation de réseaux faiblement supervisés bout-à-bout dans un mode multitâche au niveau de l'échantillon (supra-image)
AU2021349226B2 (en) Critical component detection using deep learning and attention
Zewdie et al. Classification of breast cancer types, sub-types and grade from histopathological images using deep learning technique
US20230360208A1 (en) Training end-to-end weakly supervised networks at the specimen (supra-image) level
Sankarapandian et al. A pathology deep learning system capable of triage of melanoma specimens utilizing dermatopathologist consensus as ground truth
CN115210772A (zh) 用于处理通用疾病检测的电子图像的系统和方法
Narayanan et al. DeepSDCS: Dissecting cancer proliferation heterogeneity in Ki67 digital whole slide images
Kabir et al. The utility of a deep learning-based approach in Her-2/neu assessment in breast cancer
Saito et al. Dawn of the digital diagnosis assisting system, can it open a new age for pathology?
Lang et al. Breast cancer magnification-independent multi-class histopathology classification using dual-step model
Mir et al. Artificial intelligence-based techniques for analysis of body cavity fluids: a review
Narayanan et al. Unmasking the tissue microecology of ductal carcinoma in situ with deep learning
Lloyd et al. Image analysis in surgical pathology
Saranyaraj et al. Early prediction of breast cancer based on the classification of HER‐2 and ER biomarkers using deep neural network
Parvatikar et al. Prototypical models for classifying high-risk atypical breast lesions
Grote et al. Exploring the spatial dimension of estrogen and progesterone signaling: detection of nuclear labeling in lobular epithelial cells in normal mammary glands adjacent to breast cancer
US20240212146A1 (en) Method and apparatus for analyzing pathological slide images
Selcuk et al. Automated HER2 Scoring in Breast Cancer Images Using Deep Learning and Pyramid Sampling
Qidwai et al. Color-based Fuzzy Classifier for automated detection of cancerous cells in histopathological analysis
Goswami et al. Application of Deep Learning in Cytopathology and Prostate Adenocarcinoma Diagnosis
Yuenyong et al. Detection of centroblast cells in H&E stained whole slide image based on object detection
TSAKU Texture-based deep neural network for histopathology cancer whole slide image (WSI) classification
Sreelekshmi et al. SwinCNN: An Integrated Swin Trasformer and CNN for Improved Breast Cancer Grade Classification

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21873329

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21873329

Country of ref document: EP

Kind code of ref document: A1