Is AI essential? Examining the need for deep learning in image-activated sorting of Saccharomyces cerevisiae.

Artificial intelligence (AI) has become a focal point across a multitude of societal sectors, with science not being an exception. Particularly in the life sciences, imaging flow cytometry has increasingly integrated AI for automated management and categorization of extensive cell image data. However, the necessity of AI over traditional classification methods when extending imaging flow cytometry to include cell sorting remains uncertain, primarily due to the time constraints between image acquisition and sorting actuation. AI-enabled image-activated cell sorting (IACS) methods remain substantially limited, even as recent advancements in IACS have found success while largely relying on traditional feature gating strategies. Here we assess the necessity of AI for image classification in IACS by contrasting the performance of feature gating, classical machine learning (ML), and deep learning (DL) with convolutional neural networks (CNNs) in the differentiation of Saccharomyces cerevisiae mutant images. We show that classical ML could only yield a 2.8-fold enhancement in target enrichment capability, albeit at the cost of a 13.7-fold increase in processing time. Conversely, a CNN could offer an 11.0-fold improvement in enrichment capability at an 11.5-fold increase in processing time. We further executed IACS on mixed mutant populations and quantified target strain enrichment via downstream DNA sequencing to substantiate the applicability of DL for the proposed study. Our findings validate the feasibility and value of employing DL in IACS for morphology-based genetic screening of S. cerevisiae, encouraging its incorporation in future advancements of similar technologies.

A novel preclinical model of mucopolysaccharidosis type II for developing human hematopoietic stem cell gene therapy.

A hematopoietic stem cell (HSC) gene therapy (GT) using lentiviral vectors has attracted interest as a promising treatment approach for neuropathic lysosomal storage diseases. To proceed with the clinical development of HSC-GT, evaluation of the therapeutic potential of gene-transduced human CD34+ (hCD34+) cells in vivo is one of the key issues before human trials. Here, we established an immunodeficient murine model of mucopolysaccharidosis type II (MPS II), which are transplantable human cells, and demonstrated the application of those mice in evaluating the therapeutic efficacy of gene-modified hCD34+ cells. NOG/MPS II mice, which were generated using CRISPR/Cas9, exhibited a reduction of disease-causing enzyme iduronate-2-sulfatatase (IDS) activity and the accumulation of glycosaminoglycans in their tissues. When we transplanted hCD34+ cells transduced with a lentiviral vector carrying the IDS gene into NOG/MPS II mice, a significant amelioration of biochemical pathophenotypes was observed in the visceral and neuronal tissues of those mice. In addition, grafted cells in the NOG/MPS II mice showed the oligoclonal integration pattern of the vector, but no obvious clonal dominance was detected in the mice. Our findings indicate the promising application of NOG/MPS II mice to preclinical study of HSC-GT for MPS II using human cells.

Intelligent image-activated sorting of Chlamydomonas reinhardtii by mitochondrial localization.

Organelle positioning in cells is associated with various metabolic functions and signaling in unicellular organisms. Specifically, the microalga Chlamydomonas reinhardtii repositions its mitochondria, depending on the levels of inorganic carbon. Mitochondria are typically randomly distributed in the Chlamydomonas cytoplasm, but relocate toward the cell periphery at low inorganic carbon levels. This mitochondrial relocation is linked with the carbon-concentrating mechanism, but its significance is not yet thoroughly understood. A genotypic understanding of this relocation would require a high-throughput method to isolate rare mutant cells not exhibiting this relocation. However, this task is technically challenging due to the complex intracellular morphological difference between mutant and wild-type cells, rendering conventional non-image-based high-event-rate methods unsuitable. Here, we report our demonstration of intelligent image-activated cell sorting by mitochondrial localization. Specifically, we applied an intelligent image-activated cell sorting system to sort for C. reinhardtii cells displaying no mitochondrial relocation. We trained a convolutional neural network (CNN) to distinguish the cell types based on the complex morphology of their mitochondria. The CNN was employed to perform image-activated sorting for the mutant cell type at 180 events per second, which is 1-2 orders of magnitude faster than automated microscopy with robotic pipetting, resulting in an enhancement of the concentration from 5% to 56.5% corresponding to an enrichment factor of 11.3. These results show the potential of image-activated cell sorting for connecting genotype-phenotype relations for rare-cell populations, which require a high throughput and could lead to a better understanding of metabolic functions in cells.

Ex Vivo Gene Therapy Treats Bone Complications of Mucopolysaccharidosis Type II Mouse Models through Bone Remodeling Reactivation.

Mucopolysaccharidosis type II is a disease caused by organ accumulation of glycosaminoglycans due to iduronate 2-sulfatase deficiency. This study investigated the pathophysiology of the bone complications associated with mucopolysaccharidosis II and the effect of lentivirus-mediated gene therapy of hematopoietic stem cells on bone lesions of mucopolysaccharidosis type II mouse models in comparison with enzyme replacement therapy. Bone volume, density, strength, and trabecular number were significantly higher in the untreated mucopolysaccharidosis type II mice than in wild-type mice. Accumulation of glycosaminoglycans caused reduced bone metabolism. Specifically, persistent high serum iduronate 2-sulfatase levels and release of glycosaminoglycans from osteoblasts and osteoclasts in mucopolysaccharidosis type II mice that had undergone gene therapy reactivated bone lineage remodeling, subsequently reducing bone mineral density, strength, and trabecular number to a similar degree as that observed in wild-type mice. Bone formation, resorption parameters, and mineral density in the diaphysis edge did not appear to have been affected by the irradiation administered as a pre-treatment for gene therapy. Hence, the therapeutic effect of gene therapy on the bone complications of mucopolysaccharidosis type II mice possibly outweighed that of enzyme replacement therapy in many aspects.

[Occult Breast Carcinoma and Recurrent Tumor in the Breast 14 Years after Axillary Dissection-A Case Report].

We report a patient with occult breast cancer who underwent axillary dissection as primary surgery. The patient, a 68-yearold woman, noticed a tumor measuring approximately 3 cm in diameter, in her left axilla. Biopsy of the axillary tumor revealed adenocarcinoma. Imaging studies did not detect primary lesions in the mammary gland or other organs. The patient was diagnosed with occult breast cancer and underwent axillary dissection but did not desire mastectomy or radiation therapy. The patient was closely observed thereafter. Tamoxifen was prescribed for 5 years but left breast cancer was detected 14 years after the operation. A simple mastectomy was performed. She died of respiratory failure 1 year later. Occult breast cancer may require axillary lymph node dissection and systemic therapy. Breast preservation could be an alternative treatment if followed by adequate systemic therapy and close observation.

[Surgical Resection of a Solitary Pulmonary Nodule in a Patient with Breast Cancer-A Case Report].

Solitary lung tumors after radical surgery for breast cancer often present difficulty in diagnosis and treatment. This report describes the case of a patient with a previous history of radicalsurgery for breast cancer who underwent lung surgery. Solitary pulmonary nodules should be diagnosed in patients with breast cancer, because treatments and prognoses differ between metastatic and primary tumors. At the age of 43 years, this patient underwent surgicaltreatment for breast cancer. Eighteen years later, a solitary mass was observed in the middle lobe of the right lung. Right middle lobectomy was performed using video-assisted thoracic surgery. The diagnosis was primary lung carcinoma. In case of primary lung carcinoma, radical treatment is possible through surgical resection. On the contrary, breast cancer metastasis has been known to have subtypes with characteristics that may often be different from those of the originall esions; therefore, surgicalresection helps in the reevaluation of receptor expression. Thus, early pathological diagnosis using surgical resection is useful for early diagnosis and treatment.

[Analysis of the Risk Factors of Febrile Neutropenia Among 72 Women Receiving FEC in Early Breast Cancer Chemotherapy].

In early breast cancer chemotherapy, it is important to maintain the relative dose intensity(RDI). We retrospectively ana- lyzed the incidence and risk factors of febrile neutropenia(FN)among women receiving FEC(5-fluorouracil 500mg/m2, epirubicin 100mg/m2, and cyclophosphamide 500 mg/m2)chemotherapy. Of 72 patients, 33 patients developed FN and 39 patients did not. Excluding patients in whom the nadir could not be confirmed, we classified a final total of 28 patients into the FN group and 24 into the non-FN group. The number of leukocytes was significantly lower in the FN group(1,500/mL versus 2,146/mL, p=0.05). The reduction rate of leukocytes was also significantly lower in the FN group(74.5%versus 65.0%, p=0.02). In adjuvant FEC chemotherapy, the considerable reduction of leukocytes at nadir is a risk factor of FN. To manage FN appropriately, G-CSF therapy may be considered for these patients.

[Predictors of Overall Survival after Locoregional Breast Cancer Recurrence].

We evaluated prognostic factors of locoregional breast cancer recurrence in 35 patients. The average age at the time of surgery was 58.4 years(range: 32-87 years). Of the 35 patients, 7, 17, and 11 had Stage I , II and III disease, respectively. Immunohistochemically, 25 tumors were ER+, and 10 were ER-, while 6 were HER2+, 27 were HER2-, and 2 had uncertain HER2 statuses. Their median disease-free interval(DFI), which is the intervalbetween initialsurgery and locoregional recurrence, was 29.4 months(range: 1-133 months). After locoregional relapse, 13 patients underwent surgical tumor removal, and 34 received systemic treatment. The median time-to-progression(TTP)after first-line therapy for recurrent breast cancer was 12.7 months(range: 1-185 months), and the median overall survival(OS)was 70.0 months(range: 3-313 months). Univariate analysis showed that disease stage at initial surgery, triple-negative disease, DFI, and TTP significantly affected OS, whereas ER and HER2 status, surgical margin at primary surgery, lymphovascular invasion, irradiation after initial surgery, and resection of the recurrent tumor were not significant factors. Patients with factors that predict worse prognosis after locoregional recurrence should be treated carefully.

[Lung Metastasis of Breast Cancer Five Years after Mastectomy - A Case Report].

The presence of a solitary lung tumor after radical surgery for breast cancer often causes difficulty in the diagnosis and treatment. We report a patient who had previously undergone radical surgery for breast cancer, and who underwent lung surgery. When the patient was 57 years old, she underwent surgical treatment for breast cancer. Six years later, a chest radiograph revealed a solitary mass on the upper lobe of her left lung. A left upper lobectomy was performed, utilizing videoassisted thoracic surgery. The pathological diagnosis, based on hematoxylin and eosin staining, was lung metastasis from breast cancer. The immunohistological findings revealed that the tumor was positive for estrogen receptor, progesterone receptor, and GCDFP-15, and negative for TTF-1 and Napsin A. Although the original breast cancer lesion was positive for the HER2 receptor, the metastatic lung lesion was negative. It has already been reported that the subtypes can change from 1 subtype in the original lesion to another in the metastatic lesion. Adjuvant therapy was administered based on the subtype of the metastatic lesion after the surgery. Therefore, surgical resection is useful for the purpose of reevaluating HER2 receptor status, the results ofwhich can influence the postoperative adjuvant treatment. The patient is now doing well, without any evidence ofrecurrence or metastasis 15 months after surgery.

[Treatment for Elderly Breast Cancer Patients Older than 80 Years].

Breast cancer is the leading form of cancer in women in Japan. Cases of elderly women with breast cancer have been increasing rapidly in Japan due to the increasing age of the population. We examined the clinicopathological features and prognosis of breast cancer patients over 80 years old to define an optimal treatment regimen. From January 2004 to October 2014, 43 primary breast cancer patients underwent surgery at the Chiba Rosai Hospital. The median age was 84 years. On pathological diagnosis, the median tumor diameter was 2.4 cm. The tumors were positive for estrogen and progesterone receptors in 30 and 26 patients, respectively. The median overall survival time was 78 months. Only lymph node metastasis was an important predictor of overall survival. It is important to appropriately treat elderly patients. However, there have been no clinical practice guidelines for the management of breast cancer in elderly individuals because of a lack of clinical trials including elderly patients. Elderly patients have other complications such as cardiovascular disease, diabetes, dementia, and pulmonary emphysema. Therefore, we need to make a clinical decision for each individual patient considering comorbidities, functional status, and clinicopathological characteristics of the tumor.