A Deep Learning Model to Predict Breast Implant Texture Types Using Ultrasonography Images: Feasibility Development Study.

BACKGROUND: Breast implants, including textured variants, have been widely used in aesthetic and reconstructive mammoplasty. However, the textured type, which is one of the shell texture types of breast implants, has been identified as a possible etiologic factor for lymphoma, specifically breast implant-associated anaplastic large cell lymphoma (BIA-ALCL). Identifying the shell texture type of the implant is critical to diagnosing BIA-ALCL. However, distinguishing the shell texture type can be difficult due to the loss of human memory and medical history. An alternative approach is to use ultrasonography, but this method also has limitations in quantitative assessment. OBJECTIVE: This study aims to determine the feasibility of using a deep learning model to classify the shell texture type of breast implants and make robust predictions from ultrasonography images from heterogeneous sources. METHODS: A total of 19,502 breast implant images were retrospectively collected from heterogeneous sources, including images captured from both Canon and GE devices, images of ruptured implants, and images without implants, as well as publicly available images. The Canon images were trained using ResNet-50. The model's performance on the Canon dataset was evaluated using stratified 5-fold cross-validation. Additionally, external validation was conducted using the GE and publicly available datasets. The area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (PRAUC) were calculated based on the contribution of the pixels with Gradient-weighted Class Activation Mapping (Grad-CAM). To identify the significant pixels for classification, we masked the pixels that contributed less than 10%, up to a maximum of 100%. To assess the model's robustness to uncertainty, Shannon entropy was calculated for 4 image groups: Canon, GE, ruptured implants, and without implants. RESULTS: The deep learning model achieved an average AUROC of 0.98 and a PRAUC of 0.88 in the Canon dataset. The model achieved an AUROC of 0.985 and a PRAUC of 0.748 for images captured with GE devices. Additionally, the model predicted an AUROC of 0.909 and a PRAUC of 0.958 for the publicly available dataset. This model maintained the PRAUC values for quantitative validation when masking up to 90% of the least-contributing pixels and the remnant pixels in breast shell layers. Furthermore, the prediction uncertainty increased in the following order: Canon (0.066), GE (0072), ruptured implants (0.371), and no implants (0.777). CONCLUSIONS: We have demonstrated the feasibility of using deep learning to predict the shell texture type of breast implants. This approach quantifies the shell texture types of breast implants, supporting the first step in the diagnosis of BIA-ALCL.

An atypical case of pediatric anaplastic lymphoma kinase-positive anaplastic large cell lymphoma limited to the skin on chest wall detected by ultrasound.

.

18 F-FDG PET/CT in Synovial Anaplastic Large Cell Lymphoma.

ABSTRACT: Anaplastic large cell lymphoma is an uncommon and aggressive form of peripheral T-cell lymphoma. Synovial anaplastic large cell lymphoma is very rare. We present PET/CT findings in a patient with synovial anaplastic large cell lymphoma. Intense FDG accumulation was found in irregular synovial thickening of the right knee. Biopsy of the synovium was performed and revealed anaplastic large cell lymphoma. This case demonstrates that anaplastic large cell lymphoma should be included as one of the differential diagnoses of FDG-avid synovial lesions.

Anaplastic bone lymphoma presenting as isolated back pain.

A previously healthy man in his late 20s presented with a 4-week history of insidious back pain and raised inflammatory markers. Various specialists were involved in his care including general physicians, orthopaedic surgeons and rheumatologists. After numerous investigations including imaging and two bone biopsies, an unexpected diagnosis of anaplastic large cell lymphoma emerged. This case illustrates the importance of investigating back pain with red flags thoroughly using different imaging modalities and where indicated a bone biopsy.

Xanthogranulomatous inflammation and spindle cell proliferation in response to silicone breast implant leakage.

This case study highlights the rare complications of silicone breast implants, as well as the diagnostic limitations of imaging. The patient initially presented with leakage of bilateral breast implants as discovered by a positron emission tomography (PET)-computerized tomography (CT) scan performed as part of a workup for small bowel Langerhans cell sarcoma metastases. The imaging results of the PET-CT scan revealed increased activity bilaterally with an enhancing, irregular, heterogeneously enhancing mass in the right breast. Given the clinical suspicion for breast implant-associated anaplastic large cell lymphoma, further investigation including surgical excision was undertaken. What initially was a concern for a serious complication of long-standing breast implants, fortuitously turned out to be a benign but exuberant xanthogranulomatous inflammatory reactive process. We hope that our report will add to the literature of this rare phenomenon and highlight it as a differential diagnosis of a mass in association with breast implants.

ALK-negative CNS anaplastic large cell lymphoma: case report and review of literature.

BACKGROUND: Central nervous system (CNS) lymphomas frequently pose a diagnostic challenge to physicians. CNS anaplastic large cell lymphoma (ALCL) is a rare condition. A majority (80%) of ALCLs harbour anaplastic lymphoma kinase 1 (ALK-1) mutation with only a minority testing negative for this mutation. METHODS: Here we report a rare case of ALK-negative CNS ALCL with dural involvement. We conducted a literature search using PubMed for published studies in English on cases of patients with ALCL of the brain. The keywords used were 'anaplastic large cell lymphoma', 'ALK' and 'primary central nervous system lymphoma'. RESULTS: A 63-year-old man presents with waxing and waning cranial nerve and spinal cord symptoms. MRI revealed multiple intracranial and intra-spinal lesions that were highly steroid responsive. A wide range of serum and CSF tests were non-diagnostic during three months of workup before a lesion appeared in the cervical spine that required decompression and allowed us to obtain a tissue sample. Final pathology revealed ALK-negative ALCL. There are only 24 reported adult cases to date of CNS ALCL in the English literature. To our knowledge, this is the first case of ALK-negative ALCL with primarily CNS and meningeal involvement. CONCLUSIONS: ALK-negative ALCL with CNS involvement is extremely rare, which frequently results in delayed diagnosis (average 40.5 days). The diagnostic challenge posed by this case highlights the importance of a team approach to workup and diligent patient follow-up for such a rare disease.

Subdural anaplastic large-cell lymphoma presenting as a subacute epidural hematoma on imaging: A case report.

RATIONALE: Subdural anaplastic large-cell lymphoma (SALCL) is an extremely rare subtype of primary central nervous system (CNS) lymphoma. Here, we report a very rare subdural lymphoma case, which was misdiagnosed as a subacute epidural hematoma based on the radiological examination. PATIENT CONCERNS: We present the case of an 82-year-old patient who presented with a 2-day history of headache and consciousness disorder following head injury. Computed tomography of the head revealed a fusiform isodense/slightly dense shadow under the right temporoparietal occipital cranial plate, suggesting a subacute epidural hematoma. It was initially misdiagnosed as a right traumatic subacute epidural hematoma with hemiplegia of the left limb. According to the patient's condition, an emergency craniotomy was performed to remove the hematoma. However, it was found that the lesion was located under the dura mater and was yellowish-brown with yellowish-brown liquid inside. The appearance of the lesion looked like bean curd residue. Histopathological examination diagnosed ALCL. DIAGNOSIS: SALCL presenting as a subacute epidural hematoma on imaging. INTERVENTIONS: Operation. OUTCOMES: The patient died 1 month after being discharged automatically. CONCLUSIONS: This report shows a rare radiography presentation of SALCL. SALCL can mimic the appearance of an epidural hematoma and should be regarded as a differential diagnosis even in patients with a history of craniocerebral injury and the "typical" imaging appearance of an epidural hematoma. The report is hoped to provide a scientific reference for the clinical diagnosis of subdural lymphoma.

A rare presentation of anaplastic large cell lymphoma as a cavitary pulmonary mass with hypercalcemia.

Cavitary lung lesions found on chest imaging may point to various diseases. These lesions may be caused by numerous etiologies, such as infection, inflammatory diseases, or malignancy. Thus, its etiology may be challenging to differentiate using imaging alone. Differential diagnoses are created using a combination of clinical symptoms, medical history, laboratory results, and physical examination. Primary pulmonary lymphoma and anaplastic large cell lymphoma (ALCL) are rare differentials. Here, we report a case of ALCL that initially presented with back pain, intermittent fever, hemoptysis, hypercalcemia, and bilateral multiple cavitary lung nodules. Because a cavitary pulmonary mass with sustained hypercalcemia is commonly seen in patients with squamous cell carcinomas or pulmonary tuberculosis, patients with ALCL may be misdiagnosed and undergo delayed treatment. This study highlights that ALCL should be considered in patients presenting with a cavitary pulmonary mass and hypercalcemia.

Invasive stage III breast implant-associated anaplastic large cell lymphoma successfully treated with incomplete resection.

A woman with history of bilateral breast augmentation 15 years prior presented with right breast swelling, peri-implant effusion and a palpable inferomedial mass. Effusion aspiration demonstrated pleiomorphic cells consistent with breast implant-associated anaplastic large cell lymphoma (BIA-ALCL). Further diagnostic studies confirmed stage III disease with a 4.7 cm right breast mass and fluorodeoxyglucose uptake in an internal mammary chain lymph node. The patient underwent surgery with incomplete resection due to invasion of the chest wall followed by chemotherapy and radiation therapy. BIA-ALCL typically presents as an indolent effusion, however advanced disease carries a worse prognosis. This case highlights successful treatment without recurrence past the one-year mark as well as the need for multidisciplinary management when dealing with advanced disease.

Is it Possible to Differentiate Types of Breast Implants by Imaging in the Era of Implant-associated Lymphoma?

OBJECTIVES: Breast implant-associated anaplastic large-cell lymphoma (BIA-ALCL) has been recognised in recent years, and there is extensive ongoing research. Although the exact mechanism and cause are still unclear, we now know that the disease is more associated with textured implants. To the best of our knowledge, no previous studies investigating the radiological differential of various implants have been conducted. In this essay, we aimed to demonstrate dicriminating in vitro and in vivo imaging features of variuos types of breast implant devices using mammography, ultrasound, and Magnetic Resonance Imaging (MRI). METHODS: Five different implant devices from various manufacturers with various surface textures, including smooth, micro-textured, regular macro-textured, lightweight macro-textured, and polyurethane- coated were used. In vitro mammography was performed with a digital mammogram (Amulet Innovality, Fuji, Japan), and in vitro and in vivo sonography were performed with Esaote MyLab9 using a 7.5 MHz linear probe. In vitro MRI was performed with a 1.5T magnet (Symphony TIM upgrade and Aera, Siemens Healthcare, Erlangen, Germany) with a 7-channel breast coil (Sense coil, Innova, Germany). MRI studies included fat sat T2 weighted sequences (T2WS), non-fat sat T2WS, and silicone only sequences. RESULTS: Each imaging technique had different contributions to dealing with this challenge. Mammography and MRI were limited to identifying the capsule's double bands. We could only differentiate the lightweight macro-textured implant on the mammogram as the borosilicate microspheres were represented by tiny, round lucencies within the gel. Ultrasound imaging with the proper technique was very helpful in identifying the surface. The inner capsule (implant shell) was identified as parallel double echogenic bands on the in vitro sonogram. Bands of the smooth implant were better delineated compared to the textured implants. The double echogenic bands of the polyurethane-coated implant were not even identified individually. The reverberation artifact caused by the smooth implant was the main discriminating in vivo sonographic feature of smooth implants. The hyperintense polyurethane-coated capsule was identified on fat-saturated T2WS and non-fat-saturated T2WS via in vitro MRI. The tiny hypointense microspheres of the lightweight implant were also identified on the silicone-only sequence of the in vitro MRI. CONCLUSION: In this study, we have shown that breast implant material and type may differ with the help of in vitro and in vivo imaging characteristics on different radiological modalities. These different imaging features could be used for recognising and labelling the implant type, especially macrotextured implants that are reported to be more associated with breast implant-associated anaplastic large-cell lymphoma (BIA-ALCL) compared to other types. We believe evaluating these imaging characteristics during daily practice will help radiologists become aware of the implant type and possible complications or diseases associated with that type.

Breast-implant-associated anaplastic large-cell lymphoma.

Breast-implant-associated anaplastic large-cell lymphoma (BIA-ALCL) is an uncommon, recently recognized disease that seems to occur only in relation with implants with textured surfaces. Most cases present with late-onset peri-implant effusion or fluid collections that develop more than 12 months after insertion of the implant. The diagnosis is reached by cytological analysis of fluid samples obtained by ultrasound-guided fine-needle aspiration. These patients usually have a good prognosis after surgical removal of the implant. A small percentage of patients present with a nodule or mass adjacent to the implant that usually develops late. In these cases, the diagnosis is reached by the histological analysis of core-needle biopsy specimens. These patients have a worse prognosis and require a combination of surgery and systemic chemotherapy. The main immunophenotypic characteristics of this lymphoma are intense expression of CD30 and a lack of expression of anaplastic lymphoma kinase (ALK). Here we present a case of BIA-ALCL in a patient with implants with a textured surface that presented with peri-implant effusion and incipient formation of a millimetric nodule and was treated with removal of the implant and bilateral capsulectomy. It is important to point out that the disease requires multidisciplinary management and that the Spanish Agency of Medicines and Medical Devices (AEMPS) should be notified when the diagnosis is confirmed.

Angiosarcoma arising in the capsule of a mammary silicone implant.

A 40-year-old woman with silicone implants inserted 21 years before presented with sudden onset of painful right breast swelling. Clinical examination revealed a firm swollen breast with appearance of old bruising. Ultrasound showed fluid around the implant. Cytology of the fluid showed cells with large pleomorphic nuclei with prominent nucleoli including elongated forms and very occasional vacuoles. The cell block also contained small fragments with atypical spindle cells around slit-like spaces that were positive for CD31 and CD34. MRI showed a 25 mm serpiginous area of enhancement on the inner aspect of the fibrous capsule with haematoma between the capsule and the implant. The capsule and adjacent area were excised. Histology showed angiosarcoma extending from the inner aspect of the capsule into the cavity around the implant. The location of the tumour on the inner aspect of the capsule is the same site that breast implant associated anaplastic large cell lymphomas arise and suggests a possible causal link between the implant and the angiosarcoma. This case emphasises the value of cytological assessment of fluid around breast implants and the role of cell blocks and immunohistochemistry.

Cost and clinical benefit of imaging surveillance after treatment for breast implant-associated anaplastic large cell lymphoma (BIA-ALCL).

Recent UK guidelines recommend that surveillance imaging should not be offered to patients who have undergone treatment for breast implant-associated anaplastic large cell lymphoma (BIA-ALCL) unless clinically indicated. The aim of this study was to explore the evolving practice at a tertiary referral unit and quantify the direct economic costs (DEC) associated with post-treatment BIA-ALCL routine radiological surveillance prior to adoption of the guidelines. Eleven patients were treated for BIA-ALCL between 2015 and 2020. At a median follow-up of 38 months (IQR 12-47) there were no local or distant relapses. Two patients did not have any radiological surveillance and 1 had follow-up elsewhere. The remaining 8 patients had a combination of positron emission tomography/computed tomography (PET/CT) (n = 10), CT (n = 2), breast ultrasound (n = 6), mammogram (n = 4) and breast magnetic resonance imaging (MRI) (n = 1) as routine imaging follow-up not guided by clinical concerns. Total cost of imaging was £10,396 (€12,257) with a median cost of £1953 (€2304) per patient [IQR £526-2029 (€621-2394)]. This cost could have been saved based on current guidelines recommending no routine surveillance for asymptomatic patients.

Breast implant-associated anaplastic large cell lymphoma (BIA-ALCL): a good practice guide, pictorial review, and new perspectives.

Breast implant-associated anaplastic large cell lymphoma (BIA-ALCL) is a rare but emerging T-cell non-Hodgkin lymphoma. It has two distinct subtypes, "effusion-only" or "mass-forming" disease, arising around implants in patients with in situ or previous history of textured-surface breast implants. The clinical, histopathological and imaging features are unique and nuanced as compared to primary breast malignancy and other lymphoma categories. Prompt recognition and diagnosis triggers referral to appropriate BIA-ALCL centres and initiation of treatment, with potential for excellent prognosis. Definitive management of both subtypes involves implant and capsule removal; systemic therapy is reserved for mass-forming disease and advanced-stage disease. There have been recent crucial advances in the diagnostic pathway, with publication of national and international guidelines: from the UK Medicines Healthcare products Regulatory Agency (MHRA) Plastic, Reconstructive and Aesthetic Surgery Expert Advisory Group (PRASEAG), and the United States National Comprehensive Cancer Network (NCCN). This review provides a practical guide to the clinical work-up of BIA-ALCL, enabling optimisation of the diagnostic imaging pathway, with representative cases.

Implant deformity on screening mammography, an unusual presentation of breast implant associated lymphoma.

Breast implant associated anaplastic large cell lymphoma (BIA-ALCL) is a rare condition related to textured breast implants. Recognition of characteristic imaging and pathological features are important, given the absence of symptoms can delay diagnosis, as illustrated by this case. Late-onset peri-implant effusion is commonly encountered whilst an associated mass or lymphadenopathy are rare. Clinical and radiological suspicion enables dedicated pathology work-up for diagnosis. Ultrasound is vital for initial work-up whilst MRI and PET-CT assist in staging. Surgical explantation is followed by adjuvant chemo-radiotherapy according to disease extent.

[Breast implant-associated anaplastic large cell lymphoma].

Breast implant-associated anaplastic large cell lymphoma is an uncommon malignancy associated with textured breast implants, and since 2014 13 Danish cases have been identified. Early diagnosis is important to minimise morbidity. Most patients present with swelling of the breast due to seroma within the fibrous capsule, fewer with a tumour. The diagnosis is based on cytology/histology with finding of typical anaplastic large cells, positive for CD30 and negative for anaplastic lymphoma kinase. Staging includes bone marrow examination and PET-CT scan, and a minority need systemic treatment, as argued in this review.

Relapsed Breast Implant-Associated Anaplastic Large-Cell Lymphoma Presenting as Refractory Fluid Collections With Low Uptake on FDG PET/CT Scan.

ABSTRACT: Breast implant-associated anaplastic large-cell lymphoma is a rare type of non-Hodgkin lymphoma that occurs years after placement of textured surface breast implants. Patients typically present after the development of pain, a palpable mass, or swelling. We present a case of a 45-year-old woman with recurrent breast implant-associated anaplastic large-cell lymphoma presenting as refractory fluid collections, and the unusual finding of low uptake on FDG PET/CT scan despite being confirmed by cytology.