NuInsSeg: A fully annotated dataset for nuclei instance segmentation in H&E-stained histological images.

In computational pathology, automatic nuclei instance segmentation plays an essential role in whole slide image analysis. While many computerized approaches have been proposed for this task, supervised deep learning (DL) methods have shown superior segmentation performances compared to classical machine learning and image processing techniques. However, these models need fully annotated datasets for training which is challenging to acquire, especially in the medical domain. In this work, we release one of the biggest fully manually annotated datasets of nuclei in Hematoxylin and Eosin (H&E)-stained histological images, called NuInsSeg. This dataset contains 665 image patches with more than 30,000 manually segmented nuclei from 31 human and mouse organs. Moreover, for the first time, we provide additional ambiguous area masks for the entire dataset. These vague areas represent the parts of the images where precise and deterministic manual annotations are impossible, even for human experts. The dataset and detailed step-by-step instructions to generate related segmentation masks are publicly available on the respective repositories.

Improving generalization capability of deep learning-based nuclei instance segmentation by non-deterministic train time and deterministic test time stain normalization.

With the advent of digital pathology and microscopic systems that can scan and save whole slide histological images automatically, there is a growing trend to use computerized methods to analyze acquired images. Among different histopathological image analysis tasks, nuclei instance segmentation plays a fundamental role in a wide range of clinical and research applications. While many semi- and fully-automatic computerized methods have been proposed for nuclei instance segmentation, deep learning (DL)-based approaches have been shown to deliver the best performances. However, the performance of such approaches usually degrades when tested on unseen datasets. In this work, we propose a novel method to improve the generalization capability of a DL-based automatic segmentation approach. Besides utilizing one of the state-of-the-art DL-based models as a baseline, our method incorporates non-deterministic train time and deterministic test time stain normalization, and ensembling to boost the segmentation performance. We trained the model with one single training set and evaluated its segmentation performance on seven test datasets. Our results show that the proposed method provides up to 4.9%, 5.4%, and 5.9% better average performance in segmenting nuclei based on Dice score, aggregated Jaccard index, and panoptic quality score, respectively, compared to the baseline segmentation model.

Breast MRI radiomics and machine learning-based predictions of response to neoadjuvant chemotherapy - How are they affected by variations in tumor delineation?

Manual delineation of volumes of interest (VOIs) by experts is considered the gold-standard method in radiomics analysis. However, it suffers from inter- and intra-operator variability. A quantitative assessment of the impact of variations in these delineations on the performance of the radiomics predictors is required to develop robust radiomics based prediction models. In this study, we developed radiomics models for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with two different breast cancer subtypes based on contrast-enhanced magnetic resonance imaging acquired prior to treatment (baseline MRI scans). Different mathematical operations such as erosion, smoothing, dilation, randomization, and ellipse fitting were applied to the original VOIs delineated by experts to simulate variations of segmentation masks. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. Using manual tumor VOIs and radiomics features extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 was achieved for human epidermal growth receptor 2 positive and triple-negative breast cancer, respectively. For smoothing and erosion, VOIs yielded the highest number of robust features and the best prediction performance, while ellipse fitting and dilation lead to the lowest robustness and prediction performance for both breast cancer subtypes. At most 28% of the selected features were similar to manual VOIs when different VOI delineation data were used. Differences in VOI delineation affect different steps of radiomics analysis, and their quantification is therefore important for development of standardized radiomics research.

A dual decoder U-Net-based model for nuclei instance segmentation in hematoxylin and eosin-stained histological images.

Even in the era of precision medicine, with various molecular tests based on omics technologies available to improve the diagnosis process, microscopic analysis of images derived from stained tissue sections remains crucial for diagnostic and treatment decisions. Among other cellular features, both nuclei number and shape provide essential diagnostic information. With the advent of digital pathology and emerging computerized methods to analyze the digitized images, nuclei detection, their instance segmentation and classification can be performed automatically. These computerized methods support human experts and allow for faster and more objective image analysis. While methods ranging from conventional image processing techniques to machine learning-based algorithms have been proposed, supervised convolutional neural network (CNN)-based techniques have delivered the best results. In this paper, we propose a CNN-based dual decoder U-Net-based model to perform nuclei instance segmentation in hematoxylin and eosin (H&E)-stained histological images. While the encoder path of the model is developed to perform standard feature extraction, the two decoder heads are designed to predict the foreground and distance maps of all nuclei. The outputs of the two decoder branches are then merged through a watershed algorithm, followed by post-processing refinements to generate the final instance segmentation results. Moreover, to additionally perform nuclei classification, we develop an independent U-Net-based model to classify the nuclei predicted by the dual decoder model. When applied to three publicly available datasets, our method achieves excellent segmentation performance, leading to average panoptic quality values of 50.8%, 51.3%, and 62.1% for the CryoNuSeg, NuInsSeg, and MoNuSAC datasets, respectively. Moreover, our model is the top-ranked method in the MoNuSAC post-challenge leaderboard.

Special Issue on "Advances in Skin Lesion Image Analysis Using Machine Learning Approaches".

Skin diseases are widespread and a frequent occurrence in general practice [...].

Investigating the Impact of the Bit Depth of Fluorescence-Stained Images on the Performance of Deep Learning-Based Nuclei Instance Segmentation.

Nuclei instance segmentation can be considered as a key point in the computer-mediated analysis of histological fluorescence-stained (FS) images. Many computer-assisted approaches have been proposed for this task, and among them, supervised deep learning (DL) methods deliver the best performances. An important criterion that can affect the DL-based nuclei instance segmentation performance of FS images is the utilised image bit depth, but to our knowledge, no study has been conducted so far to investigate this impact. In this work, we released a fully annotated FS histological image dataset of nuclei at different image magnifications and from five different mouse organs. Moreover, by different pre-processing techniques and using one of the state-of-the-art DL-based methods, we investigated the impact of image bit depth (i.e., eight bits vs. sixteen bits) on the nuclei instance segmentation performance. The results obtained from our dataset and another publicly available dataset showed very competitive nuclei instance segmentation performances for the models trained with 8 bit and 16 bit images. This suggested that processing 8 bit images is sufficient for nuclei instance segmentation of FS images in most cases. The dataset including the raw image patches, as well as the corresponding segmentation masks is publicly available in the published GitHub repository.

MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge.

Detecting various types of cells in and around the tumor matrix holds a special significance in characterizing the tumor micro-environment for cancer prognostication and research. Automating the tasks of detecting, segmenting, and classifying nuclei can free up the pathologists' time for higher value tasks and reduce errors due to fatigue and subjectivity. To encourage the computer vision research community to develop and test algorithms for these tasks, we prepared a large and diverse dataset of nucleus boundary annotations and class labels. The dataset has over 46,000 nuclei from 37 hospitals, 71 patients, four organs, and four nucleus types. We also organized a challenge around this dataset as a satellite event at the International Symposium on Biomedical Imaging (ISBI) in April 2020. The challenge saw a wide participation from across the world, and the top methods were able to match inter-human concordance for the challenge metric. In this paper, we summarize the dataset and the key findings of the challenge, including the commonalities and differences between the methods developed by various participants. We have released the MoNuSAC2020 dataset to the public.

CryoNuSeg: A dataset for nuclei instance segmentation of cryosectioned H&E-stained histological images.

Nuclei instance segmentation plays an important role in the analysis of hematoxylin and eosin (H&E)-stained images. While supervised deep learning (DL)-based approaches represent the state-of-the-art in automatic nuclei instance segmentation, annotated datasets are required to train these models. There are two main types of tissue processing protocols resulting in formalin-fixed paraffin-embedded samples (FFPE) and frozen tissue samples (FS), respectively. Although FFPE-derived H&E stained tissue sections are the most widely used samples, H&E staining of frozen sections derived from FS samples is a relevant method in intra-operative surgical sessions as it can be performed more rapidly. Due to differences in the preparation of these two types of samples, the derived images and in particular the nuclei appearance may be different in the acquired whole slide images. Analysis of FS-derived H&E stained images can be more challenging as rapid preparation, staining, and scanning of FS sections may lead to deterioration in image quality. In this paper, we introduce CryoNuSeg, the first fully annotated FS-derived cryosectioned and H&E-stained nuclei instance segmentation dataset. The dataset contains images from 10 human organs that were not exploited in other publicly available datasets, and is provided with three manual mark-ups to allow measuring intra-observer and inter-observer variabilities. Moreover, we investigate the effects of tissue fixation/embedding protocol (i.e., FS or FFPE) on the automatic nuclei instance segmentation performance and provide a baseline segmentation benchmark for the dataset that can be used in future research. A step-by-step guide to generate the dataset as well as the full dataset and other detailed information are made available to fellow researchers at https://github.com/masih4/CryoNuSeg.

The effects of skin lesion segmentation on the performance of dermatoscopic image classification.

BACKGROUND AND OBJECTIVE: Malignant melanoma (MM) is one of the deadliest types of skin cancer. Analysing dermatoscopic images plays an important role in the early detection of MM and other pigmented skin lesions. Among different computer-based methods, deep learning-based approaches and in particular convolutional neural networks have shown excellent classification and segmentation performances for dermatoscopic skin lesion images. These models can be trained end-to-end without requiring any hand-crafted features. However, the effect of using lesion segmentation information on classification performance has remained an open question. METHODS: In this study, we explicitly investigated the impact of using skin lesion segmentation masks on the performance of dermatoscopic image classification. To do this, first, we developed a baseline classifier as the reference model without using any segmentation masks. Then, we used either manually or automatically created segmentation masks in both training and test phases in different scenarios and investigated the classification performances. The different scenarios included approaches that exploited the segmentation masks either for cropping of skin lesion images or removing the surrounding background or using the segmentation masks as an additional input channel for model training. RESULTS: Evaluated on the ISIC 2017 challenge dataset which contained two binary classification tasks (i.e. MM vs. all and seborrheic keratosis (SK) vs. all) and based on the derived area under the receiver operating characteristic curve scores, we observed four main outcomes. Our results show that 1) using segmentation masks did not significantly improve the MM classification performance in any scenario, 2) in one of the scenarios (using segmentation masks for dilated cropping), SK classification performance was significantly improved, 3) removing all background information by the segmentation masks significantly degraded the overall classification performance, and 4) in case of using the appropriate scenario (using segmentation for dilated cropping), there is no significant difference of using manually or automatically created segmentation masks. CONCLUSIONS: We systematically explored the effects of using image segmentation on the performance of dermatoscopic skin lesion classification.

Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification.

BACKGROUND AND OBJECTIVE: Skin cancer is among the most common cancer types in the white population and consequently computer aided methods for skin lesion classification based on dermoscopic images are of great interest. A promising approach for this uses transfer learning to adapt pre-trained convolutional neural networks (CNNs) for skin lesion diagnosis. Since pre-training commonly occurs with natural images of a fixed image resolution and these training images are usually significantly smaller than dermoscopic images, downsampling or cropping of skin lesion images is required. This however may result in a loss of useful medical information, while the ideal resizing or cropping factor of dermoscopic images for the fine-tuning process remains unknown. METHODS: We investigate the effect of image size for skin lesion classification based on pre-trained CNNs and transfer learning. Dermoscopic images from the International Skin Imaging Collaboration (ISIC) skin lesion classification challenge datasets are either resized to or cropped at six different sizes ranging from 224 × 224 to 450 × 450. The resulting classification performance of three well established CNNs, namely EfficientNetB0, EfficientNetB1 and SeReNeXt-50 is explored. We also propose and evaluate a multi-scale multi-CNN (MSM-CNN) fusion approach based on a three-level ensemble strategy that utilises the three network architectures trained on cropped dermoscopic images of various scales. RESULTS: Our results show that image cropping is a better strategy compared to image resizing delivering superior classification performance at all explored image scales. Moreover, fusing the results of all three fine-tuned networks using cropped images at all six scales in the proposed MSM-CNN approach boosts the classification performance compared to a single network or a single image scale. On the ISIC 2018 skin lesion classification challenge test set, our MSM-CNN algorithm yields a balanced multi-class accuracy of 86.2% making it the currently second ranked algorithm on the live leaderboard. CONCLUSIONS: We confirm that the image size has an effect on skin lesion classification performance when employing transfer learning of CNNs. We also show that image cropping results in better performance compared to image resizing. Finally, a straightforward ensembling approach that fuses the results from images cropped at six scales and three fine-tuned CNNs is shown to lead to the best classification performance.

A Multi-Organ Nucleus Segmentation Challenge.

Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Fusing fine-tuned deep features for skin lesion classification.

Malignant melanoma is one of the most aggressive forms of skin cancer. Early detection is important as it significantly improves survival rates. Consequently, accurate discrimination of malignant skin lesions from benign lesions such as seborrheic keratoses or benign nevi is crucial, while accurate computerised classification of skin lesion images is of great interest to support diagnosis. In this paper, we propose a fully automatic computerised method to classify skin lesions from dermoscopic images. Our approach is based on a novel ensemble scheme for convolutional neural networks (CNNs) that combines intra-architecture and inter-architecture network fusion. The proposed method consists of multiple sets of CNNs of different architecture that represent different feature abstraction levels. Each set of CNNs consists of a number of pre-trained networks that have identical architecture but are fine-tuned on dermoscopic skin lesion images with different settings. The deep features of each network were used to train different support vector machine classifiers. Finally, the average prediction probability classification vectors from different sets are fused to provide the final prediction. Evaluated on the 600 test images of the ISIC 2017 skin lesion classification challenge, the proposed algorithm yields an area under receiver operating characteristic curve of 87.3% for melanoma classification and an area under receiver operating characteristic curve of 95.5% for seborrheic keratosis classification, outperforming the top-ranked methods of the challenge while being simpler compared to them. The obtained results convincingly demonstrate our proposed approach to represent a reliable and robust method for feature extraction, model fusion and classification of dermoscopic skin lesion images.

Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure.

We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-theart algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning, …), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.