Color Standardization and Stain Intensity Calibration for Whole Slide Image-Based Immunohistochemistry Assessment.

Automated quantification of human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) using whole slide imaging (WSI) is expected to eliminate subjectivity in visual assessment. However, the color intensity in WSI varies depending on the staining process and scanner device. Such variations affect the image analysis results. This paper presents methods to diminish the influence of color variation produced in the staining process using a calibrator slide consisting of peptide-coated microbeads. The calibrator slide is stained along with tissue sample slides, and the 3,3'-diaminobenzidine (DAB) color intensities of the microbeads are used for calibrating the color variation of the sample slides. An off-the-shelf image analysis tool is employed for the automated assessment, in which cells are classified by the thresholds for the membrane staining. We have adopted two methods for calibrating the color variation based on the DAB color intensities obtained from the calibrator slide: (1) thresholds for classifying the DAB membranous intensity are adjusted, and (2) the color intensity of WSI is corrected. In the experiment, the calibrator slides and tissue of breast cancer slides were stained together on different days and used to test our protocol. With the proposed protocol, the discordance in the HER2 evaluation was reduced to one slide out of 120 slides.

Yttrium-90 Activity Quantification in PET/CT-Guided Biopsy Specimens from Colorectal Hepatic Metastases Immediately after Transarterial Radioembolization Using Micro-CT and Autoradiography.

PURPOSE: To evaluate the yttrium-90 (90Y) activity distribution in biopsy tissue samples of the treated liver to quantify the dose with higher spatial resolution than positron emission tomography (PET) for accurate investigation of correlations with microscopic biological effects and to evaluate the radiation safety of this procedure. MATERIALS AND METHODS: Eighty-six core biopsy specimens were obtained from 18 colorectal liver metastases (CLMs) immediately after 90Y transarterial radioembolization (TARE) with either resin or glass microspheres using real-time 90Y PET/CT guidance in 17 patients. A high-resolution micro-computed tomography (micro-CT) scanner was used to image the microspheres in part of the specimens and allow quantification of 90Y activity directly or by calibrating autoradiography (ARG) images. The mean doses to the specimens were derived from the measured specimens' activity concentrations and from the PET/CT scan at the location of the biopsy needle tip for all cases. Staff exposures were monitored. RESULTS: The mean measured 90Y activity concentration in the CLM specimens at time of infusion was 2.4 ± 4.0 MBq/mL. The biopsies revealed higher activity heterogeneity than PET. Radiation exposure to the interventional radiologists during post-TARE biopsy procedures was minimal. CONCLUSIONS: Counting the microspheres and measuring the activity in biopsy specimens obtained after TARE are safe and feasible and can be used to determine the administered activity and its distribution in the treated and biopsied liver tissue with high spatial resolution. Complementing 90Y PET/CT imaging with this approach promises to yield more accurate direct correlation of histopathological changes and absorbed dose in the examined specimens.

Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments.

The Banff Digital Pathology Working Group (DPWG) was established with the goal to establish a digital pathology repository; develop, validate, and share models for image analysis; and foster collaborations using regular videoconferencing. During the calls, a variety of artificial intelligence (AI)-based support systems for transplantation pathology were presented. Potential collaborations in a competition/trial on AI applied to kidney transplant specimens, including the DIAGGRAFT challenge (staining of biopsies at multiple institutions, pathologists' visual assessment, and development and validation of new and pre-existing Banff scoring algorithms), were also discussed. To determine the next steps, a survey was conducted, primarily focusing on the feasibility of establishing a digital pathology repository and identifying potential hosts. Sixteen of the 35 respondents (46%) had access to a server hosting a digital pathology repository, with 2 respondents that could serve as a potential host at no cost to the DPWG. The 16 digital pathology repositories collected specimens from various organs, with the largest constituent being kidney (n = 12,870 specimens). A DPWG pilot digital pathology repository was established, and there are plans for a competition/trial with the DIAGGRAFT project. Utilizing existing resources and previously established models, the Banff DPWG is establishing new resources for the Banff community.

Three-Dimensional Vessel Segmentation in Whole-Tissue and Whole-Block Imaging Using a Deep Neural Network: Proof-of-Concept Study.

In the field of pathology, micro-computed tomography (micro-CT) has become an attractive imaging modality because it enables full analysis of the three-dimensional characteristics of a tissue sample or organ in a noninvasive manner. However, because of the complexity of the three-dimensional information, understanding would be improved by development of analytical methods and software such as those implemented for clinical CT. As the accurate identification of tissue components is critical for this purpose, we have developed a deep neural network (DNN) to analyze whole-tissue images (WTIs) and whole-block images (WBIs) of neoplastic cancer tissue using micro-CT. The aim of this study was to segment vessels from WTIs and WBIs in a volumetric segmentation method using DNN. To accelerate the segmentation process while retaining accuracy, a convolutional block in DNN was improved by introducing a residual inception block. Three colorectal tissue samples were collected and one WTI and 70 WBIs were acquired by a micro-CT scanner. The implemented segmentation method was then tested on the WTI and WBIs. As a proof-of-concept study, our method successfully segmented the vessels on all WTI and WBIs of the colorectal tissue sample. In addition, despite the large size of the images for analysis, all segmentation processes were completed in 10 minutes.

The impact of death rattle on bereaved families: not the sound itself, but the resonance with their feelings.

BACKGROUND: This study aimed to explore (i) the consistency between physician-rated and bereaved family-perceived intensity of death rattle, (ii) the relationship between intensity of death rattle and the bereaved family's distress and (iii) the bereaved family's experience and feelings related to suctioning for death rattle. METHODS: We used matched data for deceased patients from a prospective cohort study of cancer patients admitted to a palliative care unit, and their bereaved families from a nationwide questionnaire survey in Japan. The intensity of death rattle using Back's score was evaluated prospectively by physicians and retrospectively by bereaved families. RESULTS: In total, 1122 bereaved families answered (response rate: 66.7%). Of these, 297 reported the development of death rattle. The maximum intensity of death rattle evaluated by physicians and perceived by bereaved families was poorly correlated (Spearman correlation coefficient 0.188, P = 0.082). The optimal cut-off point of Back's score for detecting high-level distress was 1/2, with a low accuracy of prediction (area under the curve 0.62). More than 70% of bereaved families indicated suctioning reduced the intensity of death rattle, made patients comfortable and themselves relieved, whereas a similar proportion felt patients were in distress during suctioning. Families who felt suctioning was gently performed and discussed well whether to do suctioning with health care providers felt less needs for improvement. CONCLUSIONS: Bereaved family-perceived intensity of death rattle did not correlate to physician-evaluated intensity, and the intensity of death rattle itself seemed to poorly correlate to family distress. Gently performed suctioning based on sufficient discussion with families can help reduce family-perceived patient discomfort.

Morphine May Contribute to Improving Respiratory Failure in Severe COVID-19: A Case Report.

At present, the world is undergoing successive waves of the COVID-19 pandemic. When COVID-19 becomes severe, it causes respiratory failure and symptoms of dyspnoea. The patient's dyspnoea worsens to the IPOS of 3. One COVID-19 patient admitted to our medical institution developed severe illness characterised by hypoxaemia and dyspnoea. In addition to disease-modifying treatments such as remdesivir and dexamethasone, we administered morphine to relieve his dyspnoea. Surprisingly, we observed an improvement in both hypoxaemia and dyspnoea.

Counting mitoses: SI(ze) matters!

Mitoses are often assessed by pathologists to assist the diagnosis of cancer, and to grade malignancy, informing prognosis. Historically, this has been done by expressing the number of mitoses per n high power fields (HPFs), ignoring the fact that microscope fields may differ substantially, even at the same high power (×400) magnification. Despite a requirement to define HPF size in scientific papers, many authors fail to address this issue adequately. The problem is compounded by the switch to digital pathology systems, where ×400 equivalent fields are rectangular and also vary in the area displayed. The potential for error is considerable, and at times this may affect patient care. This is easily solved by the use of standardized international (SI) units. We, therefore, recommend that features such as mitoses are always counted per mm2, with an indication of the area to be counted and the method used (usually "hotspot" or "average") to obtain the results.

Conditions, possibility and priority for admission into inpatient hospice/palliative care units in Japan: a nationwide survey.

BACKGROUND: Known barriers to admission into inpatient hospice/palliative care units (PCUs) include poor accessibility and stringent conditions for admission. However, the exact criteria are unclear. The aim of this study was to clarify the actual conditions, possibilities and priorities for admission to PCU in Japan. METHODS: We conducted a nationwide, anonymous, self-administered questionnaire survey to the responsible physicians of all 251 PCUs in 2014. RESULTS: Responses were received from 190 institutions (response rate 76%). The most frequent condition for admission was 'either the patient or the family knows the diagnosis' [86%, 95% confidence interval (CI): 80-90]. For the conditions for admission to PCU, 10-40% fewer facilities answered that the patient's consent or understanding was required compared with those that answered the patient or family's consent was sufficient. Seventy-one percent (95% CI: 64-77) of PCUs answered that either the patient or a family member needed to agree to a do-not-resuscitate (DNR) policy. The factors most likely to result in refusal of admission to a PCU varied greatly. Ninety-four percent (95% CI: 90-97) of PCUs answered that patients who had undergone a long waiting time after applying for admission would be given higher priority, and approximately 50% of PCUs answered they gave priority to their outpatients and inpatients. CONCLUSIONS: The findings of this study should be used to modify the system so that appropriate palliative care can be provided to patients who wish to be admitted to PCU.

Using Automated Machine Learning to Predict the Mortality of Patients With COVID-19: Prediction Model Development Study.

BACKGROUND: During a pandemic, it is important for clinicians to stratify patients and decide who receives limited medical resources. Machine learning models have been proposed to accurately predict COVID-19 disease severity. Previous studies have typically tested only one machine learning algorithm and limited performance evaluation to area under the curve analysis. To obtain the best results possible, it may be important to test different machine learning algorithms to find the best prediction model. OBJECTIVE: In this study, we aimed to use automated machine learning (autoML) to train various machine learning algorithms. We selected the model that best predicted patients' chances of surviving a SARS-CoV-2 infection. In addition, we identified which variables (ie, vital signs, biomarkers, comorbidities, etc) were the most influential in generating an accurate model. METHODS: Data were retrospectively collected from all patients who tested positive for COVID-19 at our institution between March 1 and July 3, 2020. We collected 48 variables from each patient within 36 hours before or after the index time (ie, real-time polymerase chain reaction positivity). Patients were followed for 30 days or until death. Patients' data were used to build 20 machine learning models with various algorithms via autoML. The performance of machine learning models was measured by analyzing the area under the precision-recall curve (AUPCR). Subsequently, we established model interpretability via Shapley additive explanation and partial dependence plots to identify and rank variables that drove model predictions. Afterward, we conducted dimensionality reduction to extract the 10 most influential variables. AutoML models were retrained by only using these 10 variables, and the output models were evaluated against the model that used 48 variables. RESULTS: Data from 4313 patients were used to develop the models. The best model that was generated by using autoML and 48 variables was the stacked ensemble model (AUPRC=0.807). The two best independent models were the gradient boost machine and extreme gradient boost models, which had an AUPRC of 0.803 and 0.793, respectively. The deep learning model (AUPRC=0.73) was substantially inferior to the other models. The 10 most influential variables for generating high-performing models were systolic and diastolic blood pressure, age, pulse oximetry level, blood urea nitrogen level, lactate dehydrogenase level, D-dimer level, troponin level, respiratory rate, and Charlson comorbidity score. After the autoML models were retrained with these 10 variables, the stacked ensemble model still had the best performance (AUPRC=0.791). CONCLUSIONS: We used autoML to develop high-performing models that predicted the survival of patients with COVID-19. In addition, we identified important variables that correlated with mortality. This is proof of concept that autoML is an efficient, effective, and informative method for generating machine learning-based clinical decision support tools.

Banff Digital Pathology Working Group: Going digital in transplant pathology.

The Banff Digital Pathology Working Group (DPWG) was formed in the time leading up to and during the joint American Society for Histocompatibility and Immunogenetics/Banff Meeting, September 23-27, 2019, held in Pittsburgh, Pennsylvania. At the meeting, the 14th Banff Conference, presentations directly and peripherally related to the topic of "digital pathology" were presented; and discussions before, during, and after the meeting have resulted in a list of issues to address for the DPWG. Included are practice standardization, integrative approaches for study classification, scoring of histologic parameters (eg, interstitial fibrosis and tubular atrophy and inflammation), algorithm classification, and precision diagnosis (eg, molecular pathways and therapeutics). Since the meeting, a survey with international participation of mostly pathologists (81%) was conducted, showing that whole slide imaging is available at the majority of centers (71%) but that artificial intelligence (AI)/machine learning was only used in ≈12% of centers, with a wide variety of programs/algorithms employed. Digitalization is not just an end in itself. It also is a necessary precondition for AI and other approaches. Discussions at the meeting and the survey highlight the unmet need for a Banff DPWG and point the way toward future contributions that can be made.

Detection and assessment of capsular invasion, vascular invasion and lymph node metastasis volume in thyroid carcinoma using microCT scanning of paraffin tissue blocks (3D whole block imaging): a proof of concept.

In the modern era, detailed pathologic characteristics of a thyroid tumor are crucial to achieve accurate diagnosis and guide treatment. The presence of capsular invasion (CI) is diagnostic for carcinoma, whereas vascular invasion (VI) and nodal metastasis (NM) are included in risk stratification. However, the very definition of CI and VI is surrounded by controversies and an accurate assessment of NM is lacking. Whole Block Imaging (WBI) by microCT is a new imaging modality to create 3D reconstruction of whole tissue block with microscopic level resolution without the need for tissue sectioning. In this study, we aimed to define CI, VI, and NM volume using WBI by microCT. Twenty-eight paraffin blocks (PBs) from 26 thyroid tumors were scanned. Ten PBs contained CI, whereas 7 had VI. 3D microCT images were compared with whole slide images (WSI) of corresponding H&E slides. In 2 cases with VI and/or CI, WSI of serial H&E slides were obtained and underwent 3D-reconstruction to be compared with the WBI. Satellite tumor nodules beyond tumor capsule were shown to be CI by demonstrating the point of penetration using microCT and 3D reconstruction. Additional foci of CI were detected using microCT. VI was seen using microCT. Fibrin associated with tumor thrombus was not always present on serially sectioned H&E slides. WBI by microCT scanner was able to assess the volume of NM. In conclusion, WBI is able to detect CI, VI, and assess the volume of NM in thyroid carcinoma without tissue sectioning. It is the ultimate method for the complete sampling of the tumor capsule. It has the potential to increase the detection rate of CI, better define criteria for CI and VI, and provide an accurate assessment of the volume of nodal disease. This technology may impact the future practice of surgical pathology.

Whole slide imaging equivalency and efficiency study: experience at a large academic center.

Whole slide imaging is Food and Drug Administration-approved for primary diagnosis in the United States of America; however, relatively few pathology departments in the country have fully implemented an enterprise wide digital pathology system enabled for primary diagnosis. Digital pathology has significant potential to transform pathology practice with several published studies documenting some level of diagnostic equivalence between digital and conventional systems. However, whole slide imaging also has significant potential to disrupt pathology practice, due to the differences in efficiency of manipulating digital images vis-à-vis glass slides, and studies on the efficiency of actual digital pathology workload are lacking. Our randomized, equivalency and efficiency study aimed to replicate clinical workflow, comparing conventional microscopy to a complete digital pathology signout using whole slide images, evaluating the equivalency and efficiency of glass slide to whole slide image reporting, reflective of true pathology practice workloads in the clinical setting. All glass slides representing an entire day's routine clinical signout workload for six different anatomic pathology subspecialties at Memorial Sloan Kettering Cancer Center were scanned on Leica Aperio AT2 at ×40 (0.25 µm/pixel). Integration of whole slide images for each accessioned case is through an interface between the Leica eSlide manager database and the laboratory information system, Cerner CoPathPlus. Pathologists utilized a standard institution computer workstation and viewed whole slide images through an internally developed, vendor agnostic whole slide image viewer, named the "MSK Slide Viewer". Subspecialized pathologists first reported on glass slides from surgical pathology cases using routine clinical workflow. Glass slides were de-identified, scanned, and re-accessioned in the laboratory information system test environment. After a washout period of 13 weeks, pathologists reported the same clinical workload using whole slide image integrated within the laboratory information system. Intraobserver equivalency metrics included top-line diagnosis, margin status, lymphovascular and/or perineural invasion, pathology stage, and the need to order ancillary testing (i.e., recuts, immunohistochemistry). Turnaround time (efficiency) evaluation was defined by the start of each case when opened in the laboratory information system and when the case was completed for that day (i.e., case sent to signout queue or pending ancillary studies). Eight pathologists participated from the following subspecialties: bone and soft tissue, genitourinary, gastrointestinal, breast, gynecologic, and dermatopathology. Glass slides signouts comprised of 204 cases, encompassing 2091 glass slides; and digital signouts comprised of 199 cases, encompassing 2073 whole slide images. The median whole slide image file size was 1.54 GB; scan time/slide, 6 min 24 s; and scan area 32.1 × 18.52 mm. Overall diagnostic equivalency (e.g., top-line diagnosis) was 99.3% between digital and glass slide signout; however, signout using whole slide images showed a median overall 19% decrease in efficiency per case. No significant difference by reader, subspecialty, or specimen type was identified. Our experience is the most comprehensive study to date and shows high intraobserver whole slide image to glass slide equivalence in reporting of true clinical workflows and workloads. Efficiency needs to improve for digital pathology to gain more traction among pathologists.

A Study of the Growth Patterns of Breast Carcinoma Using 3D Reconstruction: A Pilot Study.

Lumpectomy with microscopically clear margins is a safe and effective approach for surgical management of breast carcinoma. Margins are positive for tumor in 18-50% of lumpectomies, as it is not possible to accurately determine the shape or microscopic borders of a tumor preoperatively or intraoperatively. We examined the 3D microanatomy and growth patterns of common breast carcinoma subtypes to provide guidance for lumpectomy surgery. Prospective consent was obtained for the use of excess tissue from patients undergoing lumpectomy or mastectomy for breast carcinoma. Tissue blocks from nine breast carcinomas were serially sectioned. Hematoxylin and eosin-stained slides at 100 µm intervals were scanned using a Nanozoomer (Hamamatsu, Japan) microscopic-resolution scanner. Three-dimensional reconstructions of tumors were created from scanned images using Reconstruct, open-access software. Breast carcinoma subtypes demonstrated characteristic growth patterns within breast tissue, which may have implications for lumpectomy surgery. Invasive ductal carcinomas showed a spherical shape, with a spiculated surface representing tumor cells infiltrating into surrounding parenchyma. Ductal carcinoma in situ appeared to spread along the duct system, creating dilated, tortuous, tumor-filled ducts. The invasive lobular carcinomas examined had a haphazard, linear, infiltrative growth pattern, different from the shape seen in ductal carcinomas. Our preliminary work suggests that invasive ductal and invasive lobular carcinomas appear to have distinct growth patterns in three dimensions and ductal carcinoma in situ appears to grow in a linear fashion along the duct network. The microanatomy studies described have the potential to guide refinements in breast lumpectomy technique.

Development of a 2D Image Reconstruction and Viewing System for Histological Images from Multiple Tissue Blocks: Towards High-Resolution Whole-Organ 3D Histological Images.

High-resolution 3D histology image reconstruction of the whole brain organ starts from reconstructing the high-resolution 2D histology images of a brain slice. In this paper, we introduced a method to automatically align the histology images of thin tissue sections cut from the multiple paraffin-embedded tissue blocks of a brain slice. For this method, we employed template matching and incorporated an optimization technique to further improve the accuracy of the 2D reconstructed image. In the template matching, we used the gross image of the brain slice as a reference to the reconstructed 2D histology image of the slice, while in the optimization procedure, we utilized the Jaccard index as the metric of the reconstruction accuracy. The results of our experiment on the initial 3 different whole-brain tissue slices showed that while the method works, it is also constrained by tissue deformations introduced during the tissue processing and slicing. The size of the reconstructed high-resolution 2D histology image of a brain slice is huge, and designing an image viewer that makes particularly efficient use of the computing power of a standard computer used in our laboratories is of interest. We also present the initial implementation of our 2D image viewer system in this paper.

The Role of Micro-CT in 3D Histology Imaging.

OBJECTIVES: 3D histology tissue modeling is a useful analytical technique for understanding anatomy and disease at the cellular level. However, the current accuracy of 3D histology technology is largely unknown, and errors, misalignment and missing information are common in 3D tissue reconstruction. We used micro-CT imaging technology to better understand these issues and the relationship between fresh tissue and its 3D histology counterpart. METHODS: We imaged formalin-fixed and 2% Lugol-stained mouse brain, human uterus and human lung tissue with micro-CT. We then conducted image analyses on the tissues before and after paraffin embedding using 3D Slicer and ImageJ software to understand how tissue changes between the fixation and embedding steps. RESULTS: We found that all tissue samples decreased in volume by 19.2-61.5% after embedding, that micro-CT imaging can be used to assess the integrity of tissue blocks, and that micro-CT analysis can help to design an optimized tissue-sectioning protocol. CONCLUSIONS: Micro-CT reference data help to identify where and to what extent tissue was lost or damaged during slide production, provides valuable anatomical information for reconstructing missing parts of a 3D tissue model, and aids in correcting reconstruction errors when fitting the image information in vivo and ex vivo.

Development of a database system and image viewer to assist in the correlation of histopathologic features and digital image analysis with clinical and molecular genetic information.

Pathologists are required to integrate data from multiple sources when making a diagnosis. Furthermore, whole slide imaging (WSI) and next generation sequencing will escalate data size and complexity. Development of well-designed databases that can allow efficient navigation between multiple data types is necessary for both clinical and research purposes. We developed and evaluated an interactive, web-based database that integrates clinical, histologic, immunohistochemical and genetic information to aid in pathologic diagnosis and interpretation with nine lung adenocarcinoma cases. To minimize sectioning artifacts, representative blocks were serially sectioned using automated tissue sectioning (Kurabo Industries, Osaka Japan) and selected slides were stained by multiple techniques, (hematoxylin and eosin [H&E], immunohistochemistry [IHC] or fluorescence in situ hybridization [FISH]). Slides were digitized by WSI scanners. An interactive relational database was designed based on a list of proposed fields covering a variety of clinical, pathologic and molecular parameters. By focusing on the three main tasks of 1.) efficient management of textual information, 2.) effective viewing of all varieties of stained whole slide images (WSI), and 3.) assistance in evaluating WSI with computer-aided diagnosis, this database prototype shows great promise for multi-modality research and diagnosis.

Republished: Importance of carcinoma-associated fibroblast-derived proteins in clinical oncology.

Carcinoma-associated fibroblast (CAF) as prominent cell type of the tumour microenvironment has complex interaction with both the cancer cells and other non-neoplastic surrounding cells. The CAF-derived regulators and extracellular matrix proteins can support cancer progression by providing a protective microenvironment for the cancer cells via reduction of chemotherapy sensitivity. On the other hand, these proteins may act as powerful prognostic markers as well as potential targets of anticancer therapy. In this review, we summarise the clinical importance of the major CAF-derived signals influencing tumour behaviour and determining the outcome of chemotherapy.

Staining correction in digital pathology by utilizing a dye amount table.

The stained colors of the tissue components are popularly used as features for image analysis. However, variations in the staining condition of the histology slides prompt variations to the color distribution of the stained tissue samples which could impact the accuracy of the analysis. In this paper, we present a method to correct the staining condition of a histology image. In the method, a look-up table (LUT) based on the dye amounts absorbed by the sample is built. The LUT can be built when either (i) the source and reference staining conditions are specified or (ii) when the user simply wants to recreate his/her preferred staining condition without specifying any reference slide. The effectiveness of the present method was evaluated in two aspects: (i) CIELAB color difference of nuclei, cytoplasm, and red blood cells, between the ten different slides of liver tissue, and (ii) classification of the different tissue components. Application of the present staining correction method reduced the color difference between the slides by an average factor of 9.8 and the classification performance of a linear discriminant classifier improved by 16.5% on the average. Results of the paired t test statistical analysis further showed that the reduction in the CIELAB color difference between the slides and the improvement in the classifier's performance when staining correction was implemented is significant at p < 0.001.

Consistency and standardization of color in medical imaging: a consensus report.

This article summarizes the consensus reached at the Summit on Color in Medical Imaging held at the Food and Drug Administration (FDA) on May 8-9, 2013, co-sponsored by the FDA and ICC (International Color Consortium). The purpose of the meeting was to gather information on how color is currently handled by medical imaging systems to identify areas where there is a need for improvement, to define objective requirements, and to facilitate consensus development of best practices. Participants were asked to identify areas of concern and unmet needs. This summary documents the topics that were discussed at the meeting and recommendations that were made by the participants. Key areas identified where improvements in color would provide immediate tangible benefits were those of digital microscopy, telemedicine, medical photography (particularly ophthalmic and dental photography), and display calibration. Work in these and other related areas has been started within several professional groups, including the creation of the ICC Medical Imaging Working Group.